Abstract
Ranking functions that are used in decision systems often produce disparate results for different populations because of bias in the underlying data. Addressing, and compensating for, these disparate outcomes is a critical problem for fair decision-making. Recent compensatory measures have mostly focused on opaque transformations of the ranking functions to satisfy fairness guarantees or on the use of quotas or set-asides to guarantee a minimum number of positive outcomes to members of underrepresented groups. In this paper we propose easily explainable data-driven compensatory measures for ranking functions. Our measures rely on the generation of bonus points given to members of underrepresented groups to address disparity in the ranking function. The bonus points can be set in advance, and can be combined, allowing for considering the intersections of representations and giving better transparency to stakeholders. We propose efficient sampling-based algorithms to calculate the number of bonus points to minimize disparity. We validate our algorithms using real-world school admissions and recidivism datasets, and compare our results with that of existing fair ranking algorithms.
Forecasting, capturing and activation of carbon-dioxide (CO$_2$): Integration of Time Series Analysis, Machine Learning, and Material Design
Abstract
This study provides a comprehensive time series analysis of daily industry-specific, country-wise CO$_2$ emissions from January 2019 to February 2023. The research focuses on the Power, Industry, Ground Transport, Domestic Aviation, and International Aviation sectors in European countries (EU27 & UK, Italy, Germany, Spain) and India, utilizing near-real-time activity data from the Carbon Monitor research initiative. To identify regular emission patterns, the data from the year 2020 is excluded due to the disruptive effects caused by the COVID-19 pandemic. The study then performs a principal component analysis (PCA) to determine the key contributors to CO$_2$ emissions. The analysis reveals that the Power, Industry, and Ground Transport sectors account for a significant portion of the variance in the dataset. A 7-day moving averaged dataset is employed for further analysis to facilitate robust predictions. This dataset captures both short-term and long-term trends and enhances the quality of the data for prediction purposes. The study utilizes Long Short-Term Memory (LSTM) models on the 7-day moving averaged dataset to effectively predict emissions and provide insights for policy decisions, mitigation strategies, and climate change efforts. During the training phase, the stability and convergence of the LSTM models are ensured, which guarantees their reliability in the testing phase. The evaluation of the loss function indicates this reliability. The model achieves high efficiency, as demonstrated by $R^2$ values ranging from 0.8242 to 0.995 for various countries and sectors. Furthermore, there is a proposal for utilizing scandium and boron/aluminium-based thin films as exceptionally efficient materials for capturing CO$_2$ (with a binding energy range from -3.0 to -3.5 eV). These materials are shown to surpass the affinity of graphene and boron nitride sheets in this regard.
DBGSA: A Novel Data Adaptive Bregman Clustering Algorithm
Abstract
With the development of Big data technology, data analysis has become increasingly important. Traditional clustering algorithms such as K-means are highly sensitive to the initial centroid selection and perform poorly on non-convex datasets. In this paper, we address these problems by proposing a data-driven Bregman divergence parameter optimization clustering algorithm (DBGSA), which combines the Universal Gravitational Algorithm to bring similar points closer in the dataset. We construct a gravitational coefficient equation with a special property that gradually reduces the influence factor as the iteration progresses. Furthermore, we introduce the Bregman divergence generalized power mean information loss minimization to identify cluster centers and build a hyperparameter identification optimization model, which effectively solves the problems of manual adjustment and uncertainty in the improved dataset. Extensive experiments are conducted on four simulated datasets and six real datasets. The results demonstrate that DBGSA significantly improves the accuracy of various clustering algorithms by an average of 63.8\% compared to other similar approaches like enhanced clustering algorithms and improved datasets. Additionally, a three-dimensional grid search was established to compare the effects of different parameter values within threshold conditions, and it was discovered the parameter set provided by our model is optimal. This finding provides strong evidence of the high accuracy and robustness of the algorithm.
Domain preserving and strongly converging explicit scheme for the stochastic SIS epidemic model
Authors: Yiannis Kiouvrekis, Ioannis S. Stamatiou
Subjects: Numerical Analysis (math.NA); Probability (math.PR)
Abstract
In this article, we construct a numerical method for a stochastic version of the Susceptible Infected Susceptible (SIS) epidemic model, expressed by a suitable stochastic differential equation (SDE), by using the semi-discrete method to a suitable transformed process. We prove the strong convergence of the proposed method, with order $1,$ and examine its stability properties. Since SDEs generally lack analytical solutions, numerical techniques are commonly employed. Hence, the research will seek numerical solutions for existing stochastic models by constructing suitable numerical schemes and comparing them with other schemes. The objective is to achieve a qualitative and efficient approach to solving the equations. Additionally, for models that have not yet been proposed for stochastic modeling using SDEs, the research will formulate them appropriately, conduct theoretical analysis of the model properties, and subsequently solve the corresponding SDEs.
Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models
Authors: Mayee F. Chen, Nicholas Roberts, Kush Bhatia, Jue Wang, Ce Zhang, Frederic Sala, Christopher Ré
Abstract
The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new framework based on a simple hypothesis: just as humans acquire interdependent skills in a deliberate order, language models also follow a natural order when learning a set of skills from their training data. If such an order exists, it can be utilized for improved understanding of LMs and for data-efficient training. Using this intuition, our framework formalizes the notion of a skill and of an ordered set of skills in terms of the associated data. First, using both synthetic and real data, we demonstrate that these ordered skill sets exist, and that their existence enables more advanced skills to be learned with less data when we train on their prerequisite skills. Second, using our proposed framework, we introduce an online data sampling algorithm, Skill-It, over mixtures of skills for both continual pre-training and fine-tuning regimes, where the objective is to efficiently learn multiple skills in the former and an individual skill in the latter. On the LEGO synthetic in the continual pre-training setting, Skill-It obtains 36.5 points higher accuracy than random sampling. On the Natural Instructions dataset in the fine-tuning setting, Skill-It reduces the validation loss on the target skill by 13.6% versus training on data associated with the target skill itself. We apply our skills framework on the recent RedPajama dataset to continually pre-train a 3B-parameter LM, achieving higher accuracy on the LM Evaluation Harness with 1B tokens than the baseline approach of sampling uniformly over data sources with 3B tokens.
A grid-overlay finite difference method for the fractional Laplacian on arbitrary bounded domains
Abstract
A grid-overlay finite difference method is proposed for the numerical approximation of the fractional Laplacian on arbitrary bounded domains. The method uses an unstructured simplicial mesh and an overlay uniform grid for the underlying domain and constructs the approximation based on a uniform-grid finite difference approximation and a data transfer from the unstructured mesh to the uniform grid. The method takes full advantage of both uniform-grid finite difference approximation in efficient matrix-vector multiplication via the fast Fourier transform and unstructured meshes for complex geometries. It is shown that its stiffness matrix is similar to a symmetric and positive definite matrix and thus invertible if the data transfer has full column rank and positive column sums. Piecewise linear interpolation is studied as a special example for the data transfer. It is proved that the full column rank and positive column sums of linear interpolation is guaranteed if the spacing of the uniform grid is smaller than or equal to a positive bound proportional to the minimum element height of the unstructured mesh. Moreover, a sparse preconditioner is proposed for the iterative solution of the resulting linear system for the homogeneous Dirichlet problem of the fractional Laplacian. Numerical examples demonstrate that the new method has similar convergence behavior as existing finite difference and finite element methods and that the sparse preconditioning is effective. Furthermore, the new method can readily be incorporated with existing mesh adaptation strategies. Numerical results obtained by combining with the so-called MMPDE moving mesh method are also presented.
Integrating Offline Reinforcement Learning with Transformers for Sequential Recommendation
Authors: Xumei Xi, Yuke Zhao, Quan Liu, Liwen Ouyang, Yang Wu
Abstract
We consider the problem of sequential recommendation, where the current recommendation is made based on past interactions. This recommendation task requires efficient processing of the sequential data and aims to provide recommendations that maximize the long-term reward. To this end, we train a farsighted recommender by using an offline RL algorithm with the policy network in our model architecture that has been initialized from a pre-trained transformer model. The pre-trained model leverages the superb ability of the transformer to process sequential information. Compared to prior works that rely on online interaction via simulation, we focus on implementing a fully offline RL framework that is able to converge in a fast and stable way. Through extensive experiments on public datasets, we show that our method is robust across various recommendation regimes, including e-commerce and movie suggestions. Compared to state-of-the-art supervised learning algorithms, our algorithm yields recommendations of higher quality, demonstrating the clear advantage of combining RL and transformers.
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
Abstract
We release MiDaS v3.1 for monocular depth estimation, offering a variety of new models based on different encoder backbones. This release is motivated by the success of transformers in computer vision, with a large variety of pretrained vision transformers now available. We explore how using the most promising vision transformers as image encoders impacts depth estimation quality and runtime of the MiDaS architecture. Our investigation also includes recent convolutional approaches that achieve comparable quality to vision transformers in image classification tasks. While the previous release MiDaS v3.0 solely leverages the vanilla vision transformer ViT, MiDaS v3.1 offers additional models based on BEiT, Swin, SwinV2, Next-ViT and LeViT. These models offer different performance-runtime tradeoffs. The best model improves the depth estimation quality by 28% while efficient models enable downstream tasks requiring high frame rates. We also describe the general process for integrating new backbones. A video summarizing the work can be found at https://youtu.be/UjaeNNFf9sE and the code is available at https://github.com/isl-org/MiDaS.
Single Channel Speech Enhancement Using U-Net Spiking Neural Networks
Abstract
Speech enhancement (SE) is crucial for reliable communication devices or robust speech recognition systems. Although conventional artificial neural networks (ANN) have demonstrated remarkable performance in SE, they require significant computational power, along with high energy costs. In this paper, we propose a novel approach to SE using a spiking neural network (SNN) based on a U-Net architecture. SNNs are suitable for processing data with a temporal dimension, such as speech, and are known for their energy-efficient implementation on neuromorphic hardware. As such, SNNs are thus interesting candidates for real-time applications on devices with limited resources. The primary objective of the current work is to develop an SNN-based model with comparable performance to a state-of-the-art ANN model for SE. We train a deep SNN using surrogate-gradient-based optimization and evaluate its performance using perceptual objective tests under different signal-to-noise ratios and real-world noise conditions. Our results demonstrate that the proposed energy-efficient SNN model outperforms the Intel Neuromorphic Deep Noise Suppression Challenge (Intel N-DNS Challenge) baseline solution and achieves acceptable performance compared to an equivalent ANN model.
PSOFuzz: Fuzzing Processors with Particle Swarm Optimization
Abstract
Hardware security vulnerabilities in computing systems compromise the security defenses of not only the hardware but also the software running on it. Recent research has shown that hardware fuzzing is a promising technique to efficiently detect such vulnerabilities in large-scale designs such as modern processors. However, the current fuzzing techniques do not adjust their strategies dynamically toward faster and higher design space exploration, resulting in slow vulnerability detection, evident through their low design coverage. To address this problem, we propose PSOFuzz, which uses particle swarm optimization (PSO) to schedule the mutation operators and to generate initial input programs dynamically with the objective of detecting vulnerabilities quickly. Unlike traditional PSO, which finds a single optimal solution, we use a modified PSO that dynamically computes the optimal solution for selecting mutation operators required to explore new design regions in hardware. We also address the challenge of inefficient initial input generation by employing PSO-based input generation. Including these optimizations, our final formulation outperforms fuzzers without PSO. Experiments show that PSOFuzz achieves up to 15.25$\times$ speedup for vulnerability detection and up to 2.22$\times$ speedup for coverage compared to the state-of-the-art simulation-based hardware fuzzer.
Technical note: ShinyAnimalCV: open-source cloud-based web application for object detection, segmentation, and three-dimensional visualization of animals using computer vision
Authors: Jin Wang, Yu Hu, Lirong Xiang, Gota Morota, Samantha A. Brooks, Carissa L. Wickens, Emily K. Miller-Cushon, Haipeng Yu
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Abstract
Computer vision (CV), a non-intrusive and cost-effective technology, has furthered the development of precision livestock farming by enabling optimized decision-making through timely and individualized animal care. The availability of affordable two- and three-dimensional camera sensors, combined with various machine learning and deep learning algorithms, has provided a valuable opportunity to improve livestock production systems. However, despite the availability of various CV tools in the public domain, applying these tools to animal data can be challenging, often requiring users to have programming and data analysis skills, as well as access to computing resources. Moreover, the rapid expansion of precision livestock farming is creating a growing need to educate and train animal science students in CV. This presents educators with the challenge of efficiently demonstrating the complex algorithms involved in CV. Thus, the objective of this study was to develop ShinyAnimalCV, an open-source cloud-based web application. This application provides a user-friendly interface for performing CV tasks, including object segmentation, detection, three-dimensional surface visualization, and extraction of two- and three-dimensional morphological features. Nine pre-trained CV models using top-view animal data are included in the application. ShinyAnimalCV has been deployed online using cloud computing platforms. The source code of ShinyAnimalCV is available on GitHub, along with detailed documentation on training CV models using custom data and deploying ShinyAnimalCV locally to allow users to fully leverage the capabilities of the application. ShinyAnimalCV can contribute to CV research and teaching in the animal science community.
SPICE Modeling of Memcomputing Logic Gates
Authors: Y. V. Pershin
Subjects: Emerging Technologies (cs.ET); Disordered Systems and Neural Networks (cond-mat.dis-nn)
Abstract
Memcomputing logic gates generalize the traditional Boolean logic gates for operation in the reverse direction. According to the literature, this functionality enables the efficient solution of computationally-intensive problems including factorization and NP-complete problems. To approach the deployment of memcomputing gates in hardware, this paper introduces SPICE models of memcomputing logic gates following their original definition. Using these models, we demonstrate the behavior of single gates as well as small self-organizing circuits. We also correct some inconsistencies in the prior literature. Importantly, the correct schematics of dynamic correction module is reported here for the first time. Our work makes memcomputing more accessible to those who are interested in this emerging computing technology.
Open Problems in Computer Vision for Wilderness SAR and The Search for Patricia Wu-Murad
Abstract
This paper details the challenges in applying two computer vision systems, an EfficientDET supervised learning model and the unsupervised RX spectral classifier, to 98.9 GB of drone imagery from the Wu-Murad wilderness search and rescue (WSAR) effort in Japan and identifies 3 directions for future research. There have been at least 19 proposed approaches and 3 datasets aimed at locating missing persons in drone imagery, but only 3 approaches (2 unsupervised and 1 of an unknown structure) are referenced in the literature as having been used in an actual WSAR operation. Of these proposed approaches, the EfficientDET architecture and the unsupervised spectral RX classifier were selected as the most appropriate for this setting. The EfficientDET model was applied to the HERIDAL dataset and despite achieving performance that is statistically equivalent to the state-of-the-art, the model fails to translate to the real world in terms of false positives (e.g., identifying tree limbs and rocks as people), and false negatives (e.g., failing to identify members of the search team). The poor results in practice for algorithms that showed good results on datasets suggest 3 areas of future research: more realistic datasets for wilderness SAR, computer vision models that are capable of seamlessly handling the variety of imagery that can be collected during actual WSAR operations, and better alignment on performance measures.
Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum
Authors: Amnon Geifman, Daniel Barzilai, Ronen Basri, Meirav Galun
Abstract
Wide neural networks are biased towards learning certain functions, influencing both the rate of convergence of gradient descent (GD) and the functions that are reachable with GD in finite training time. As such, there is a great need for methods that can modify this bias according to the task at hand. To that end, we introduce Modified Spectrum Kernels (MSKs), a novel family of constructed kernels that can be used to approximate kernels with desired eigenvalues for which no closed form is known. We leverage the duality between wide neural networks and Neural Tangent Kernels and propose a preconditioned gradient descent method, which alters the trajectory of GD. As a result, this allows for a polynomial and, in some cases, exponential training speedup without changing the final solution. Our method is both computationally efficient and simple to implement.
Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition
Abstract
We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy. For (1), we use a large language model (LLM) to guide high-level planning, and sampling-based robot planners (e.g. motion or grasp samplers) for generating diverse and rich manipulation trajectories. To robustify this data-collection process, the LLM also infers a code-snippet for the success condition of each task, simultaneously enabling the data-collection process to detect failure and retry as well as the automatic labeling of trajectories with success/failure. For (2), we extend the diffusion policy single-task behavior-cloning approach to multi-task settings with language conditioning. Finally, we propose a new multi-task benchmark with 18 tasks across five domains to test long-horizon behavior, common-sense reasoning, tool-use, and intuitive physics. We find that our distilled policy successfully learned the robust retrying behavior in its data collection policy, while improving absolute success rates by 34.8% on average across five domains. The benchmark, code, and qualitative results are on our website https://www.cs.columbia.edu/~huy/scalingup/
Speed Reading Tool Powered by Artificial Intelligence for Students with ADHD, Dyslexia, or Short Attention Span
Authors: Megat Irfan Zackry Bin Ismail Ahmad Nazran bin Yusri Muhammad Hafizzul Bin Abdul Manap Muhammad Muizzuddin Bin Kamarozaman
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Abstract
This paper presents a novel approach to assist students with dyslexia, ADHD, and short attention span in digesting any text-based information more efficiently. The proposed solution utilizes the Multilayer Perceptron (MLP) algorithm for complex text processing and summarization tasks. The tool leverages the T5 (Text-to-Text Transfer Transformer) model from Hugging Face, which treats every NLP task as a text generation task. The model is fine-tuned on specific tasks using a smaller dataset. The NLTK's Punkt Sentence Tokenizer is used to divide a text into a list of sentences. The application is served using Flask, a lightweight web server and framework. The tool also applies principles from Bionic Reading to enhance readability, which includes a bolding function and adjustments to line, word, and character spacing. The paper discusses the methodology, implementation, and results of the AI-based speed reading tool.
Adversarial Sleeping Bandit Problems with Multiple Plays: Algorithm and Ranking Application
Abstract
This paper presents an efficient algorithm to solve the sleeping bandit with multiple plays problem in the context of an online recommendation system. The problem involves bounded, adversarial loss and unknown i.i.d. distributions for arm availability. The proposed algorithm extends the sleeping bandit algorithm for single arm selection and is guaranteed to achieve theoretical performance with regret upper bounded by $\bigO(kN^2\sqrt{T\log T})$, where $k$ is the number of arms selected per time step, $N$ is the total number of arms, and $T$ is the time horizon.
Limiting Moments of Autocorrelation Demerit Factors of Binary Sequences
Authors: Daniel J. Katz, Miriam E. Ramirez
Subjects: Information Theory (cs.IT); Discrete Mathematics (cs.DM); Signal Processing (eess.SP); Combinatorics (math.CO); Probability (math.PR)
Abstract
An aperiodic binary sequence of length $\ell$ is written as $f=\ldots,f_{-1},f_0,f_1,\ldots$ with $f_j \in {-1,1}$ when $0 \leq j < \ell$ and and $f_j=0$ otherwise. Various problems in engineering and natural science demand binary sequences that do not resemble translates of themselves. The autocorrelation of $f$ at shift $s$ is the inner product of $f$ with the sequence obtained by translating $f$ by $s$ places. The demerit factor of $f$ is the sum of the squares of the autocorrelations at all nonzero shifts for the sequence obtained by normalizing $f$ to unit Euclidean norm. Low demerit factor therefore indicates low self-similarity under translation. We endow the $2^\ell$ binary sequences of length $\ell$ with uniform probability measure and consider the distribution of their demerit factors. Earlier works used combinatorial techniques to find exact formulas for the mean, variance, and skewness of the distribution as a function of $\ell$. These revealed that for $\ell \geq 4$, the $p$th central moment of this distribution is positive for every $p \geq 2$. This article shows that every $p$th central moment is a quasi-polynomial function of $\ell$ with rational coefficients divided by $\ell^{2 p}$. It also shows that, in the limit as $\ell$ tends to infinity, the $p$th standardized moment is the same as that of the standard normal distribution.
HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting
Abstract
Traffic forecasting, which aims to predict traffic conditions based on historical observations, has been an enduring research topic and is widely recognized as an essential component of intelligent transportation. Recent proposals on Spatial-Temporal Graph Neural Networks (STGNNs) have made significant progress by combining sequential models with graph convolution networks. However, due to high complexity issues, STGNNs only focus on short-term traffic forecasting, e.g., 1-hour forecasting, while ignoring more practical long-term forecasting. In this paper, we make the first attempt to explore long-term traffic forecasting, e.g., 1-day forecasting. To this end, we first reveal its unique challenges in exploiting multi-scale representations. Then, we propose a novel Hierarchical U-net TransFormer (HUTFormer) to address the issues of long-term traffic forecasting. HUTFormer consists of a hierarchical encoder and decoder to jointly generate and utilize multi-scale representations of traffic data. Specifically, for the encoder, we propose window self-attention and segment merging to extract multi-scale representations from long-term traffic data. For the decoder, we design a cross-scale attention mechanism to effectively incorporate multi-scale representations. In addition, HUTFormer employs an efficient input embedding strategy to address the complexity issues. Extensive experiments on four traffic datasets show that the proposed HUTFormer significantly outperforms state-of-the-art traffic forecasting and long time series forecasting baselines.
TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation
Authors: Moon Ye-Bin, Jisoo Kim, Hongyeob Kim, Kilho Son, Tae-Hyun Oh
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Recent label mix-based augmentation methods have shown their effectiveness in generalization despite their simplicity, and their favorable effects are often attributed to semantic-level augmentation. However, we found that they are vulnerable to highly skewed class distribution, because scarce data classes are rarely sampled for inter-class perturbation. We propose TextManiA, a text-driven manifold augmentation method that semantically enriches visual feature spaces, regardless of data distribution. TextManiA augments visual data with intra-class semantic perturbation by exploiting easy-to-understand visually mimetic words, i.e., attributes. To this end, we bridge between the text representation and a target visual feature space, and propose an efficient vector augmentation. To empirically support the validity of our design, we devise two visualization-based analyses and show the plausibility of the bridge between two different modality spaces. Our experiments demonstrate that TextManiA is powerful in scarce samples with class imbalance as well as even distribution. We also show compatibility with the label mix-based approaches in evenly distributed scarce data.
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
Authors: Chenfeng Xu, Bichen Wu, Ji Hou, Sam Tsai, Ruilong Li, Jialiang Wang, Wei Zhan, Zijian He, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input. Unlike existing indoor 3D detection methods that struggle to model scene geometry, our method makes novel use of NeRF in an end-to-end manner to explicitly estimate 3D geometry, thereby improving 3D detection performance. Specifically, to avoid the significant extra latency associated with per-scene optimization of NeRF, we introduce sufficient geometry priors to enhance the generalizability of NeRF-MLP. Furthermore, we subtly connect the detection and NeRF branches through a shared MLP, enabling an efficient adaptation of NeRF to detection and yielding geometry-aware volumetric representations for 3D detection. Our method outperforms state-of-the-arts by 3.9 mAP and 3.1 mAP on the ScanNet and ARKITScenes benchmarks, respectively. We provide extensive analysis to shed light on how NeRF-Det works. As a result of our joint-training design, NeRF-Det is able to generalize well to unseen scenes for object detection, view synthesis, and depth estimation tasks without requiring per-scene optimization. Code is available at \url{https://github.com/facebookresearch/NeRF-Det}.
Metric-Based In-context Learning: A Case Study in Text Simplification
Authors: Subha Vadlamannati, Gözde Gül Şahin
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Abstract
In-context learning (ICL) for large language models has proven to be a powerful approach for many natural language processing tasks. However, determining the best method to select examples for ICL is nontrivial as the results can vary greatly depending on the quality, quantity, and order of examples used. In this paper, we conduct a case study on text simplification (TS) to investigate how to select the best and most robust examples for ICL. We propose Metric-Based in-context Learning (MBL) method that utilizes commonly used TS metrics such as SARI, compression ratio, and BERT-Precision for selection. Through an extensive set of experiments with various-sized GPT models on standard TS benchmarks such as TurkCorpus and ASSET, we show that examples selected by the top SARI scores perform the best on larger models such as GPT-175B, while the compression ratio generally performs better on smaller models such as GPT-13B and GPT-6.7B. Furthermore, we demonstrate that MBL is generally robust to example orderings and out-of-domain test sets, and outperforms strong baselines and state-of-the-art finetuned language models. Finally, we show that the behaviour of large GPT models can be implicitly controlled by the chosen metric. Our research provides a new framework for selecting examples in ICL, and demonstrates its effectiveness in text simplification tasks, breaking new ground for more accurate and efficient NLG systems.
The Unweighted and Weighted Reverse Shortest Path Problem for Disk Graphs
Authors: Haim Kaplan, Matthew J. Katz, Rachel Saban, Micha Sharir
Abstract
We study the reverse shortest path problem on disk graphs in the plane. In this problem we consider the proximity graph of a set of $n$ disks in the plane of arbitrary radii: In this graph two disks are connected if the distance between them is at most some threshold parameter $r$. The case of intersection graphs is a special case with $r=0$. We give an algorithm that, given a target length $k$, computes the smallest value of $r$ for which there is a path of length at most $k$ between some given pair of disks in the proximity graph. Our algorithm runs in $O^(n^{5/4})$ randomized expected time, which improves to $O^(n^{6/5})$ for unit disk graphs, where all the disks have the same radius. Our technique is robust and can be applied to many variants of the problem. One significant variant is the case of weighted proximity graphs, where edges are assigned real weights equal to the distance between the disks or between their centers, and $k$ is replaced by a target weight $w$; that is, we seek a path whose length is at most $w$. In other variants, we want to optimize a parameter different from $r$, such as a scale factor of the radii of the disks. The main technique for the decision version of the problem (determining whether the graph with a given $r$ has the desired property) is based on efficient implementations of BFS (for the unweighted case) and of Dijkstra's algorithm (for the weighted case), using efficient data structures for maintaining the bichromatic closest pair for certain bicliques and several distance functions. The optimization problem is then solved by combining the resulting decision procedure with enhanced variants of the interval shrinking and bifurcation technique of [4].
Abstract
Order-Sorted Feature (OSF) logic is a knowledge representation and reasoning language based on function-denoting feature symbols and set-denoting sort symbols ordered in a subsumption lattice. OSF logic allows the construction of record-like terms that represent classes of entities and that are themselves ordered in a subsumption relation. The unification algorithm for such structures provides an efficient calculus of type subsumption, which has been applied in computational linguistics and implemented in constraint logic programming languages such as LOGIN and LIFE and automated reasoners such as CEDAR. This work generalizes OSF logic to a fuzzy setting. We give a flexible definition of a fuzzy subsumption relation which generalizes Zadeh's inclusion between fuzzy sets. Based on this definition we define a fuzzy semantics of OSF logic where sort symbols and OSF terms denote fuzzy sets. We extend the subsumption relation to OSF terms and prove that it constitutes a fuzzy partial order with the property that two OSF terms are subsumed by one another in the crisp sense if and only if their subsumption degree is greater than 0. We show how to find the greatest lower bound of two OSF terms by unifying them and how to compute the subsumption degree between two OSF terms, and we provide the complexity of these operations.
Prediction of wind turbines power with physics-informed neural networks and evidential uncertainty quantification
Authors: Alfonso Gijón, Ainhoa Pujana-Goitia, Eugenio Perea, Miguel Molina-Solana, Juan Gómez-Romero
Abstract
The ever-growing use of wind energy makes necessary the optimization of turbine operations through pitch angle controllers and their maintenance with early fault detection. It is crucial to have accurate and robust models imitating the behavior of wind turbines, especially to predict the generated power as a function of the wind speed. Existing empirical and physics-based models have limitations in capturing the complex relations between the input variables and the power, aggravated by wind variability. Data-driven methods offer new opportunities to enhance wind turbine modeling of large datasets by improving accuracy and efficiency. In this study, we used physics-informed neural networks to reproduce historical data coming from 4 turbines in a wind farm, while imposing certain physical constraints to the model. The developed models for regression of the power, torque, and power coefficient as output variables showed great accuracy for both real data and physical equations governing the system. Lastly, introducing an efficient evidential layer provided uncertainty estimations of the predictions, proved to be consistent with the absolute error, and made possible the definition of a confidence interval in the power curve.
Quinpi: Integrating stiff hyperbolic systems with implicit high order finite volume schemes
Authors: Gabriella Puppo, Matteo Semplice, Giuseppe Visconti
Abstract
Many interesting physical problems described by systems of hyperbolic conservation laws are stiff, and thus impose a very small time-step because of the restrictive CFL stability condition. In this case, one can exploit the superior stability properties of implicit time integration which allows to choose the time-step only from accuracy requirements, and thus avoid the use of small time-steps. We discuss an efficient framework to devise high order implicit schemes for stiff hyperbolic systems without tailoring it to a specific problem. The nonlinearity of high order schemes, due to space- and time-limiting procedures which control nonphysical oscillations, makes the implicit time integration difficult, e.g.~because the discrete system is nonlinear also on linear problems. This nonlinearity of the scheme is circumvented as proposed in (Puppo et al., Comm.~Appl.~Math.~\& Comput., 2023) for scalar conservation laws, where a first order implicit predictor is computed to freeze the nonlinear coefficients of the essentially non-oscillatory space reconstruction, and also to achieve limiting in time. In addition, we propose a novel conservative flux-based a-posteriori time-limiting procedure using numerical entropy indicators to detect troubled cells. The numerical tests involve classical and artificially devised stiff problems using the Euler's system of gas-dynamics.
Singularity Distance Computations of 3-RPR Manipulators Using Intrinsic Metrics
Abstract
We present an efficient algorithm for computing the closest singular configuration to each non-singular pose of a 3-RPR planar manipulator performing a 1-parametric motion. By considering a 3-RPR manipulator as a planar framework, one can use methods from rigidity theory to compute the singularity distance with respect to an intrinsic metric. There are different design options as the platform/base can be seen as a triangular plate or as a pin-jointed triangular bar structure. Moreover, we also allow the additional possibility of pinning down the base/platform triangle to the fixed/moving system thus it cannot be deformed. For the resulting nine interpretations, we compute the corresponding intrinsic metrics based on the total elastic strain energy density of the framework using the physical concept of Green-Lagrange strain. The global optimization problem of finding the closest singular configuration with respect to these metrics is solved by using tools from numerical algebraic geometry. The proposed algorithm is demonstrated based on an example.
New Interaction Paradigm for Complex EDA Software Leveraging GPT
Abstract
In the rapidly growing field of electronic design automation (EDA), professional software such as KiCad, Cadence , and Altium Designer provide increasingly extensive design functionalities. However, the intricate command structure and high learning curve create a barrier, particularly for novice printed circuit board (PCB) designers. This results in difficulties in selecting appropriate functions or plugins for varying design purposes, compounded by the lack of intuitive learning methods beyond traditional documentation, videos, and online forums. To address this challenge, an artificial intelligence (AI) interaction assist plugin for EDA software named SmartonAl is developed here, also KiCad is taken as the first example. SmartonAI is inspired by the HuggingGPT framework and employs large language models, such as GPT and BERT, to facilitate task planning and execution. On receiving a designer request, SmartonAI conducts a task breakdown and efficiently executes relevant subtasks, such as analysis of help documentation paragraphs and execution of different plugins, along with leveraging the built-in schematic and PCB manipulation functions in both SmartonAl itself and software. Our preliminary results demonstrate that SmartonAI can significantly streamline the PCB design process by simplifying complex commands into intuitive language-based interactions. By harnessing the powerful language capabilities of ChatGPT and the rich design functions of KiCad, the plugin effectively bridges the gap between complex EDA software and user-friendly interaction. Meanwhile, the new paradigm behind SmartonAI can also extend to other complex software systems, illustrating the immense potential of AI-assisted user interfaces in advancing digital interactions across various domains.
Semantic Image Completion and Enhancement using GANs
Abstract
Semantic inpainting or image completion alludes to the task of inferring arbitrary large missing regions in images based on image semantics. Since the prediction of image pixels requires an indication of high-level context, this makes it significantly tougher than image completion, which is often more concerned with correcting data corruption and removing entire objects from the input image. On the other hand, image enhancement attempts to eliminate unwanted noise and blur from the image, along with sustaining most of the image details. Efficient image completion and enhancement model should be able to recover the corrupted and masked regions in images and then refine the image further to increase the quality of the output image. Generative Adversarial Networks (GAN), have turned out to be helpful in picture completion tasks. In this chapter, we will discuss the underlying GAN architecture and how they can be used used for image completion tasks.
Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation
Abstract
Training an image captioner without annotated image-sentence pairs has gained traction in recent years. Previous approaches can be categorized into two strategies: crawling sentences from mismatching corpora and aligning them with the given images as pseudo annotations, or pre-training the captioner using external image-text pairs. However, the aligning setting seems to reach its performance limit due to the quality problem of pairs, and pre-training requires significant computational resources. To address these challenges, we propose a new strategy ``LPM + retrieval-augmented learning" where the prior knowledge from large pre-trained models (LPMs) is leveraged as supervision, and a retrieval process is integrated to further reinforce its effectiveness. Specifically, we introduce Retrieval-augmented Pseudo Sentence Generation (RaPSG), which adopts an efficient approach to retrieve highly relevant short region descriptions from the mismatching corpora and use them to generate a variety of pseudo sentences with distinct representations as well as high quality via LPMs. In addition, a fluency filter and a CLIP-guided training objective are further introduced to facilitate model optimization. Experimental results demonstrate that our method surpasses the SOTA pre-training model (Flamingo3B) by achieving a CIDEr score of 78.1 (+5.1) while utilizing only 0.3% of its trainable parameters (1.3B VS 33M). Importantly, our approach eliminates the need of computationally expensive pre-training processes on external datasets (e.g., the requirement of 312M image-text pairs for Flamingo3B). We further show that with a simple extension, the generated pseudo sentences can be deployed as weak supervision to boost the 1% semi-supervised image caption benchmark up to 93.4 CIDEr score (+8.9) which showcases the versatility and effectiveness of our approach.
Fair Machine Unlearning: Data Removal while Mitigating Disparities
Authors: Alex Oesterling, Jiaqi Ma, Flavio P. Calmon, Hima Lakkaraju
Abstract
As public consciousness regarding the collection and use of personal information by corporations grows, it is of increasing importance that consumers be active participants in the curation of corporate datasets. In light of this, data governance frameworks such as the General Data Protection Regulation (GDPR) have outlined the right to be forgotten as a key principle allowing individuals to request that their personal data be deleted from the databases and models used by organizations. To achieve forgetting in practice, several machine unlearning methods have been proposed to address the computational inefficiencies of retraining a model from scratch with each unlearning request. While efficient online alternatives to retraining, it is unclear how these methods impact other properties critical to real-world applications, such as fairness. In this work, we propose the first fair machine unlearning method that can provably and efficiently unlearn data instances while preserving group fairness. We derive theoretical results which demonstrate that our method can provably unlearn data instances while maintaining fairness objectives. Extensive experimentation with real-world datasets highlight the efficacy of our method at unlearning data instances while preserving fairness.
SPC5: an efficient SpMV framework vectorized using ARM SVE and x86 AVX-512
Authors: Evann Regnault, Berenger Bramas
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC)
Abstract
The sparse matrix/vector product (SpMV) is a fundamental operation in scientific computing. Having access to an efficient SpMV implementation is therefore critical, if not mandatory, to solve challenging numerical problems. The ARM-based AFX64 CPU is a modern hardware component that equips one of the fastest supercomputers in the world. This CPU supports the Scalable Vector Extension (SVE) vectorization technology, which has been less investigated than the classic x86 instruction set architectures. In this paper, we describe how we ported the SPC5 SpMV framework on AFX64 by converting AVX512 kernels to SVE. In addition, we present performance results by comparing our kernels against a standard CSR kernel for both Intel-AVX512 and Fujitsu-ARM-SVE architectures.
MATNilm: Multi-appliance-task Non-intrusive Load Monitoring with Limited Labeled Data
Abstract
Non-intrusive load monitoring (NILM) identifies the status and power consumption of various household appliances by disaggregating the total power usage signal of an entire house. Efficient and accurate load monitoring facilitates user profile establishment, intelligent household energy management, and peak load shifting. This is beneficial for both the end-users and utilities by improving the overall efficiency of a power distribution network. Existing approaches mainly focus on developing an individual model for each appliance. Those approaches typically rely on a large amount of household-labeled data which is hard to collect. In this paper, we propose a multi-appliance-task framework with a training-efficient sample augmentation (SA) scheme that boosts the disaggregation performance with limited labeled data. For each appliance, we develop a shared-hierarchical split structure for its regression and classification tasks. In addition, we also propose a two-dimensional attention mechanism in order to capture spatio-temporal correlations among all appliances. With only one-day training data and limited appliance operation profiles, the proposed SA algorithm can achieve comparable test performance to the case of training with the full dataset. Finally, simulation results show that our proposed approach features a significantly improved performance over many baseline models. The relative errors can be reduced by more than 50\% on average. The codes of this work are available at https://github.com/jxiong22/MATNilm
Contrastive Knowledge Amalgamation for Unsupervised Image Classification
Authors: Shangde Gao, Yichao Fu, Ke Liu, Yuqiang Han
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Knowledge amalgamation (KA) aims to learn a compact student model to handle the joint objective from multiple teacher models that are are specialized for their own tasks respectively. Current methods focus on coarsely aligning teachers and students in the common representation space, making it difficult for the student to learn the proper decision boundaries from a set of heterogeneous teachers. Besides, the KL divergence in previous works only minimizes the probability distribution difference between teachers and the student, ignoring the intrinsic characteristics of teachers. Therefore, we propose a novel Contrastive Knowledge Amalgamation (CKA) framework, which introduces contrastive losses and an alignment loss to achieve intra-class cohesion and inter-class separation.Contrastive losses intra- and inter- models are designed to widen the distance between representations of different classes. The alignment loss is introduced to minimize the sample-level distribution differences of teacher-student models in the common representation space.Furthermore, the student learns heterogeneous unsupervised classification tasks through soft targets efficiently and flexibly in the task-level amalgamation. Extensive experiments on benchmarks demonstrate the generalization capability of CKA in the amalgamation of specific task as well as multiple tasks. Comprehensive ablation studies provide a further insight into our CKA.
Likely, Light, and Accurate Context-Free Clusters-based Trajectory Prediction
Authors: Tiago Rodrigues de Almeida, Oscar Martinez Mozos
Abstract
Autonomous systems in the road transportation network require intelligent mechanisms that cope with uncertainty to foresee the future. In this paper, we propose a multi-stage probabilistic approach for trajectory forecasting: trajectory transformation to displacement space, clustering of displacement time series, trajectory proposals, and ranking proposals. We introduce a new deep feature clustering method, underlying self-conditioned GAN, which copes better with distribution shifts than traditional methods. Additionally, we propose novel distance-based ranking proposals to assign probabilities to the generated trajectories that are more efficient yet accurate than an auxiliary neural network. The overall system surpasses context-free deep generative models in human and road agents trajectory data while performing similarly to point estimators when comparing the most probable trajectory.
Abstract
The core reasoning task for datalog engines is materialization, the evaluation of a datalog program over a database alongside its physical incorporation into the database itself. The de-facto method of computing it, is through the recursive application of inference rules. Due to it being a costly operation, it is a must for datalog engines to provide incremental materialization, that is, to adjust the computation to new data, instead of restarting from scratch. One of the major caveats, is that deleting data is notoriously more involved than adding, since one has to take into account all possible data that has been entailed from what is being deleted. Differential Dataflow is a computational model that provides efficient incremental maintenance, notoriously with equal performance between additions and deletions, and work distribution, of iterative dataflows. In this paper we investigate the performance of materialization with three reference datalog implementations, out of which one is built on top of a lightweight relational engine, and the two others are differential-dataflow and non-differential versions of the same rewrite algorithm, with the same optimizations.
DNN-MG: A Hybrid Neural Network/Finite Element Method with Applications to 3D Simulations of the Navier-Stokes Equations
Authors: Nils Margenberg, Robert Jendersie, Christian Lessig, Thomas Richter
Abstract
We extend and analyze the deep neural network multigrid solver (DNN-MG) for the Navier-Stokes equations in three dimensions. The idea of the method is to augment of finite element simulations on coarse grids with fine scale information obtained using deep neural networks. This network operates locally on small patches of grid elements. The local approach proves to be highly efficient, since the network can be kept (relatively) small and since it can be applied in parallel on all grid patches. However, the main advantage of the local approach is the inherent good generalizability of the method. Since the network is only ever trained on small sub-areas, it never ``sees'' the global problem and thus does not learn a false bias. We describe the method with a focus on the interplay between finite element method and deep neural networks. Further, we demonstrate with numerical examples the excellent efficiency of the hybrid approach, which allows us to achieve very high accuracies on coarse grids and thus reduce the computation time by orders of magnitude.
ArcGPT: A Large Language Model Tailored for Real-world Archival Applications
Abstract
Archives play a crucial role in preserving information and knowledge, and the exponential growth of such data necessitates efficient and automated tools for managing and utilizing archive information resources. Archival applications involve managing massive data that are challenging to process and analyze. Although LLMs have made remarkable progress in diverse domains, there are no publicly available archives tailored LLM. Addressing this gap, we introduce ArcGPT, to our knowledge, the first general-purpose LLM tailored to the archival field. To enhance model performance on real-world archival tasks, ArcGPT has been pre-trained on massive and extensive archival domain data. Alongside ArcGPT, we release AMBLE, a benchmark comprising four real-world archival tasks. Evaluation on AMBLE shows that ArcGPT outperforms existing state-of-the-art models, marking a substantial step forward in effective archival data management. Ultimately, ArcGPT aims to better serve the archival community, aiding archivists in their crucial role of preserving and harnessing our collective information and knowledge.
Lookahead data-gathering strategies for online adaptive model reduction of transport-dominated problems
Authors: Rodrigo Singh, Wayne Isaac Tan Uy, Benjamin Peherstorfer
Subjects: Numerical Analysis (math.NA); Computational Engineering, Finance, and Science (cs.CE)
Abstract
Online adaptive model reduction efficiently reduces numerical models of transport-dominated problems by updating reduced spaces over time, which leads to nonlinear approximations on latent manifolds that can achieve a faster error decay than classical linear model reduction methods that keep reduced spaces fixed. Critical for online adaptive model reduction is coupling the full and reduced model to judiciously gather data from the full model for adapting the reduced spaces so that accurate approximations of the evolving full-model solution fields can be maintained. In this work, we introduce lookahead data-gathering strategies that predict the next state of the full model for adapting reduced spaces towards dynamics that are likely to be seen in the immediate future. Numerical experiments demonstrate that the proposed lookahead strategies lead to accurate reduced models even for problems where previously introduced data-gathering strategies that look back in time fail to provide predictive models. The proposed lookahead strategies also improve the robustness and stability of online adaptive reduced models.
Knot Theory and Error-Correcting Codes
Authors: Altan B. Kilic, Anne Nijsten, Ruud Pellikaan, Alberto Ravagnani
Subjects: Information Theory (cs.IT); Algebraic Topology (math.AT); General Topology (math.GN)
Abstract
This paper builds a novel bridge between algebraic coding theory and mathematical knot theory, with applications in both directions. We give methods to construct error-correcting codes starting from the colorings of a knot, describing through a series of results how the properties of the knot translate into code parameters. We show that knots can be used to obtain error-correcting codes with prescribed parameters and an efficient decoding algorithm.
Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving
Authors: Peter Bauer, Arij Bouazizi, Ulrich Kressel, Fabian B. Flohr
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Abstract
Accurate 3D human pose estimation (3D HPE) is crucial for enabling autonomous vehicles (AVs) to make informed decisions and respond proactively in critical road scenarios. Promising results of 3D HPE have been gained in several domains such as human-computer interaction, robotics, sports and medical analytics, often based on data collected in well-controlled laboratory environments. Nevertheless, the transfer of 3D HPE methods to AVs has received limited research attention, due to the challenges posed by obtaining accurate 3D pose annotations and the limited suitability of data from other domains. We present a simple yet efficient weakly supervised approach for 3D HPE in the AV context by employing a high-level sensor fusion between camera and LiDAR data. The weakly supervised setting enables training on the target datasets without any 2D/3D keypoint labels by using an off-the-shelf 2D joint extractor and pseudo labels generated from LiDAR to image projections. Our approach outperforms state-of-the-art results by up to $\sim$ 13% on the Waymo Open Dataset in the weakly supervised setting and achieves state-of-the-art results in the supervised setting.
Text-guided Foundation Model Adaptation for Pathological Image Classification
Authors: Yunkun Zhang, Jin Gao, Mu Zhou, Xiaosong Wang, Yu Qiao, Shaoting Zhang, Dequan Wang
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Abstract
The recent surge of foundation models in computer vision and natural language processing opens up perspectives in utilizing multi-modal clinical data to train large models with strong generalizability. Yet pathological image datasets often lack biomedical text annotation and enrichment. Guiding data-efficient image diagnosis from the use of biomedical text knowledge becomes a substantial interest. In this paper, we propose to Connect Image and Text Embeddings (CITE) to enhance pathological image classification. CITE injects text insights gained from language models pre-trained with a broad range of biomedical texts, leading to adapt foundation models towards pathological image understanding. Through extensive experiments on the PatchGastric stomach tumor pathological image dataset, we demonstrate that CITE achieves leading performance compared with various baselines especially when training data is scarce. CITE offers insights into leveraging in-domain text knowledge to reinforce data-efficient pathological image classification. Code is available at https://github.com/Yunkun-Zhang/CITE.
GET3D--: Learning GET3D from Unconstrained Image Collections
Abstract
The demand for efficient 3D model generation techniques has grown exponentially, as manual creation of 3D models is time-consuming and requires specialized expertise. While generative models have shown potential in creating 3D textured shapes from 2D images, their applicability in 3D industries is limited due to the lack of a well-defined camera distribution in real-world scenarios, resulting in low-quality shapes. To overcome this limitation, we propose GET3D--, the first method that directly generates textured 3D shapes from 2D images with unknown pose and scale. GET3D-- comprises a 3D shape generator and a learnable camera sampler that captures the 6D external changes on the camera. In addition, We propose a novel training schedule to stably optimize both the shape generator and camera sampler in a unified framework. By controlling external variations using the learnable camera sampler, our method can generate aligned shapes with clear textures. Extensive experiments demonstrate the efficacy of GET3D--, which precisely fits the 6D camera pose distribution and generates high-quality shapes on both synthetic and realistic unconstrained datasets.
Solving Data Quality Problems with Desbordante: a Demo
Authors: George Chernishev, Michael Polyntsov, Anton Chizhov, Kirill Stupakov, Ilya Shchuckin, Alexander Smirnov, Maxim Strutovsky, Alexey Shlyonskikh, Mikhail Firsov, Stepan Manannikov, Nikita Bobrov, Daniil Goncharov, Ilia Barutkin, Vladislav Shalnev, Kirill Muraviev, Anna Rakhmukova, Dmitriy Shcheka, Anton Chernikov, Mikhail Vyrodov, Kurbatov Yaroslav, Maxim Fofanov, Belokonnyi Sergei, Anosov Pavel, Arthur Saliou, Eduard Gaisin, Kirill Smirnov
Abstract
Data profiling is an essential process in modern data-driven industries. One of its critical components is the discovery and validation of complex statistics, including functional dependencies, data constraints, association rules, and others. However, most existing data profiling systems that focus on complex statistics do not provide proper integration with the tools used by contemporary data scientists. This creates a significant barrier to the adoption of these tools in the industry. Moreover, existing systems were not created with industrial-grade workloads in mind. Finally, they do not aim to provide descriptive explanations, i.e. why a given pattern is not found. It is a significant issue as it is essential to understand the underlying reasons for a specific pattern's absence to make informed decisions based on the data. Because of that, these patterns are effectively rest in thin air: their application scope is rather limited, they are rarely used by the broader public. At the same time, as we are going to demonstrate in this presentation, complex statistics can be efficiently used to solve many classic data quality problems. Desbordante is an open-source data profiler that aims to close this gap. It is built with emphasis on industrial application: it is efficient, scalable, resilient to crashes, and provides explanations. Furthermore, it provides seamless Python integration by offloading various costly operations to the C++ core, not only mining. In this demonstration, we show several scenarios that allow end users to solve different data quality problems. Namely, we showcase typo detection, data deduplication, and data anomaly detection scenarios.
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
Authors: Bo Shen, Jiaxin Zhang, Taihong Chen, Daoguang Zan, Bing Geng, An Fu, Muhan Zeng, Ailun Yu, Jichuan Ji, Jingyang Zhao, Yuenan Guo, Qianxiang Wang
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Programming Languages (cs.PL); Software Engineering (cs.SE)
Abstract
Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task. Various approaches have been proposed to boost the code generation performance of pre-trained Code LLMs, such as supervised fine-tuning, instruction tuning, reinforcement learning, etc. In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark. Furthermore, through an extensive evaluation on CoderEval and LeetCode benchmarks, we show that PanGu-Coder2 consistently outperforms all previous Code LLMs.
Efficient Interaction-Aware Interval Analysis of Neural Network Feedback Loops
Authors: Saber Jafarpour, Akash Harapanahalli, Samuel Coogan
Subjects: Systems and Control (eess.SY); Machine Learning (cs.LG); Optimization and Control (math.OC)
Abstract
In this paper, we propose a computationally efficient framework for interval reachability of neural network controlled systems. Our approach builds upon inclusion functions for the neural network controller and the open-loop system. We observe that many state-of-the-art neural network verifiers can produce inclusion functions for neural networks. We introduce and analyze a new class of inclusion functions for the open-loop dynamics based on bounds of the function Jacobian that is particularly suitable for capturing the interactions between systems and neural network controllers. Next, for any dynamical system, we use inclusion functions to construct an embedding system with twice the number of states as the original system. We show that a single trajectory of this embedding system provides hyper-rectangular over-approximations of reachable sets. We then propose two approaches for constructing a closed-loop embedding system for a neural network controlled dynamical system that accounts for the interaction between the system and the controller in different ways. The interconnection-based approach accounts for the worst-case evolution of each coordinate separately by substituting the neural network inclusion function into the open-loop embedding system. The interaction-based approach uses the newly introduced class of Jacobian-based inclusion functions to fully capture first-order interactions between the system and the controller. Finally, we implement our approach in a Python framework called \texttt{ReachMM} and show that on several existing benchmarks, our methods outperform the existing approaches in the literature. We also demonstrate the scalability of our method on a vehicle platooning example with up to $200$ states.
A localized orthogonal decomposition strategy for hybrid discontinuous Galerkin methods
Abstract
We formulate and analyze a multiscale method for an elliptic problem with an oscillatory coefficient based on a skeletal (hybrid) formulation. More precisely, we employ hybrid discontinuous Galerkin approaches and combine them with the localized orthogonal decomposition methodology to obtain a coarse-scale skeletal method that effectively includes fine-scale information. This work is a first step to reliably merge hybrid skeletal formulations and localized orthogonal decomposition and unite the advantages of both strategies. Numerical experiments are presented to illustrate the theoretical findings.
Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
Authors: Or Sharir, Anima Anandkumar
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL); Machine Learning (stat.ML)
Abstract
Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited. Re-running the model each time is expensive, even with compression techniques like knowledge distillation, pruning, or quantization. Instead, we take an incremental computing approach, looking to reuse calculations as the inputs change. However, the dense connectivity of conventional architectures poses a major obstacle to incremental computation, as even minor input changes cascade through the network and restrict information reuse. To address this, we use vector quantization to discretize intermediate values in the network, which filters out noisy and unnecessary modifications to hidden neurons, facilitating the reuse of their values. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of the modified inputs. Our experiments with adapting the OPT-125M pre-trained language model demonstrate comparable accuracy on document classification while requiring 12.1X (median) fewer operations for processing sequences of atomic edits.
Abstract
We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. TransNormerLLM evolves from the previous linear attention architecture TransNormer by making advanced modifications that include positional embedding, linear attention acceleration, gating mechanism, tensor normalization, inference acceleration and stabilization. Specifically, we use LRPE together with an exponential decay to avoid attention dilution issues while allowing the model to retain global interactions between tokens. Additionally, we propose Lightning Attention, a cutting-edge technique that accelerates linear attention by more than twice in runtime and reduces memory usage by a remarkable four times. To further enhance the performance of TransNormer, we leverage a gating mechanism to smooth training and a new tensor normalization scheme to accelerate the model, resulting in an impressive acceleration of over 20%. Furthermore, we have developed a robust inference algorithm that ensures numerical stability and consistent inference speed, regardless of the sequence length, showcasing superior efficiency during both training and inference stages. Scalability is at the heart of our model's design, enabling seamless deployment on large-scale clusters and facilitating expansion to even more extensive models, all while maintaining outstanding performance metrics. Rigorous validation of our model design is achieved through a series of comprehensive experiments on our self-collected corpus, boasting a size exceeding 6TB and containing over 2 trillion tokens. To ensure data quality and relevance, we implement a new self-cleaning strategy to filter our collected data. Our pre-trained models will be released to foster community advancements in efficient LLMs.
Gzip versus bag-of-words for text classification with KNN
Abstract
The effectiveness of compression distance in KNN-based text classification ('gzip') has recently garnered lots of attention. In this note, we show that similar or better effectiveness can be achieved with simpler means, and text compression may not be necessary. Indeed, we find that a simple 'bag-of-words' matching can achieve similar or better accuracy, and is more efficient.
FLiCR: A Fast and Lightweight LiDAR Point Cloud Compression Based on Lossy RI
Authors: Jin Heo, Christopher Phillips, Ada Gavrilovska
Subjects: Multimedia (cs.MM); Distributed, Parallel, and Cluster Computing (cs.DC)
Abstract
Light detection and ranging (LiDAR) sensors are becoming available on modern mobile devices and provide a 3D sensing capability. This new capability is beneficial for perceptions in various use cases, but it is challenging for resource-constrained mobile devices to use the perceptions in real-time because of their high computational complexity. In this context, edge computing can be used to enable LiDAR online perceptions, but offloading the perceptions on the edge server requires a low-latency, lightweight, and efficient compression due to the large volume of LiDAR point clouds data. This paper presents FLiCR, a fast and lightweight LiDAR point cloud compression method for enabling edge-assisted online perceptions. FLiCR is based on range images (RI) as an intermediate representation (IR), and dictionary coding for compressing RIs. FLiCR achieves its benefits by leveraging lossy RIs, and we show the efficiency of bytestream compression is largely improved with quantization and subsampling. In addition, we identify the limitation of current quality metrics for presenting the entropy of a point cloud, and introduce a new metric that reflects both point-wise and entropy-wise qualities for lossy IRs. The evaluation results show FLiCR is more suitable for edge-assisted real-time perceptions than the existing LiDAR compressions, and we demonstrate the effectiveness of our compression and metric with the evaluations on 3D object detection and LiDAR SLAM.
Abstract
Large language models (LLMs) are now highly capable at a diverse range of tasks. This paper studies whether or not GPT-4, one such LLM, is capable of assisting researchers in the field of adversarial machine learning. As a case study, we evaluate the robustness of AI-Guardian, a recent defense to adversarial examples published at IEEE S&P 2023, a top computer security conference. We completely break this defense: the proposed scheme does not increase robustness compared to an undefended baseline. We write none of the code to attack this model, and instead prompt GPT-4 to implement all attack algorithms following our instructions and guidance. This process was surprisingly effective and efficient, with the language model at times producing code from ambiguous instructions faster than the author of this paper could have done. We conclude by discussing (1) the warning signs present in the evaluation that suggested to us AI-Guardian would be broken, and (2) our experience with designing attacks and performing novel research using the most recent advances in language modeling.
Samplable Anonymous Aggregation for Private Federated Data Analysis
Authors: Kunal Talwar, Shan Wang, Audra McMillan, Vojta Jina, Vitaly Feldman, Bailey Basile, Aine Cahill, Yi Sheng Chan, Mike Chatzidakis, Junye Chen, Oliver Chick, Mona Chitnis, Suman Ganta, Yusuf Goren, Filip Granqvist, Kristine Guo, Frederic Jacobs, Omid Javidbakht, Albert Liu, Richard Low, Dan Mascenik, Steve Myers, David Park, Wonhee Park, Gianni Parsa, Tommy Pauly, Christian Priebe, Rehan Rishi, Guy Rothblum, Michael Scaria, Linmao Song, Congzheng Song, Karl Tarbe, Sebastian Vogt, Luke Winstrom, Shundong Zhou
Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
Abstract
We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Our first contribution is to propose a simple primitive that allows for efficient implementation of several commonly used algorithms, and allows for privacy accounting that is close to that in the central setting without requiring the strong trust assumptions it entails. Second, we propose a system architecture that implements this primitive and perform a security analysis of the proposed system.
A Sparse Quantized Hopfield Network for Online-Continual Memory
Authors: Nick Alonso, Jeff Krichmar
Subjects: Neural and Evolutionary Computing (cs.NE); Neurons and Cognition (q-bio.NC)
Abstract
An important difference between brains and deep neural networks is the way they learn. Nervous systems learn online where a stream of noisy data points are presented in a non-independent, identically distributed (non-i.i.d.) way. Further, synaptic plasticity in the brain depends only on information local to synapses. Deep networks, on the other hand, typically use non-local learning algorithms and are trained in an offline, non-noisy, i.i.d. setting. Understanding how neural networks learn under the same constraints as the brain is an open problem for neuroscience and neuromorphic computing. A standard approach to this problem has yet to be established. In this paper, we propose that discrete graphical models that learn via an online maximum a posteriori learning algorithm could provide such an approach. We implement this kind of model in a novel neural network called the Sparse Quantized Hopfield Network (SQHN). We show that SQHNs outperform state-of-the-art neural networks on associative memory tasks, outperform these models in online, non-i.i.d. settings, learn efficiently with noisy inputs, and are better than baselines on a novel episodic memory task.
Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
Authors: Kecheng Zheng, Wei Wu, Ruili Feng, Kai Zhu, Jiawei Liu, Deli Zhao, Zheng-Jun Zha, Wei Chen, Yujun Shen
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which masks the network parameters through a learnable selection. Inspired by neural pathways, we argue that the knowledge required by a downstream task already exists in the pre-trained weights but just gets concealed in the upstream pre-training stage. To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen. When updating the mask, we introduce a novel gradient dropout strategy to regularize the parameter selection, in order to prevent the model from forgetting old knowledge and overfitting the downstream data. Experimental results on 11 datasets demonstrate the consistent superiority of our method over previous alternatives. It is noteworthy that we manage to deliver 18.73% performance improvement compared to the zero-shot CLIP via masking an average of only 2.56% parameters. Furthermore, our method is synergistic with most existing parameter-efficient tuning methods and can boost the performance on top of them. Project page can be found here (https://wuw2019.github.io/RMT/).
Abstract
The isomorphism problem is a fundamental problem in network analysis, which involves capturing both low-order and high-order structural information. In terms of extracting low-order structural information, graph isomorphism algorithms analyze the structural equivalence to reduce the solver space dimension, which demonstrates its power in many applications, such as protein design, chemical pathways, and community detection. For the more commonly occurring high-order relationships in real-life scenarios, the problem of hypergraph isomorphism, which effectively captures these high-order structural relationships, cannot be straightforwardly addressed using graph isomorphism methods. Besides, the existing hypergraph kernel methods may suffer from high memory consumption or inaccurate sub-structure identification, thus yielding sub-optimal performance. In this paper, to address the abovementioned problems, we first propose the hypergraph Weisfiler-Lehman test algorithm for the hypergraph isomorphism test problem by generalizing the Weisfiler-Lehman test algorithm from graphs to hypergraphs. Secondly, based on the presented algorithm, we propose a general hypergraph Weisfieler-Lehman kernel framework and implement two instances, which are Hypergraph Weisfeiler-Lehamn Subtree Kernel and Hypergraph Weisfeiler-Lehamn Hyperedge Kernel. In order to fulfill our research objectives, a comprehensive set of experiments was meticulously designed, including seven graph classification datasets and 12 hypergraph classification datasets. Results on hypergraph classification datasets show significant improvements compared to other typical kernel-based methods, which demonstrates the effectiveness of the proposed methods. In our evaluation, we found that our proposed methods outperform the second-best method in terms of runtime, running over 80 times faster when handling complex hypergraph structures.
PSOFuzz: Fuzzing Processors with Particle Swarm Optimization
Abstract
Hardware security vulnerabilities in computing systems compromise the security defenses of not only the hardware but also the software running on it. Recent research has shown that hardware fuzzing is a promising technique to efficiently detect such vulnerabilities in large-scale designs such as modern processors. However, the current fuzzing techniques do not adjust their strategies dynamically toward faster and higher design space exploration, resulting in slow vulnerability detection, evident through their low design coverage. To address this problem, we propose PSOFuzz, which uses particle swarm optimization (PSO) to schedule the mutation operators and to generate initial input programs dynamically with the objective of detecting vulnerabilities quickly. Unlike traditional PSO, which finds a single optimal solution, we use a modified PSO that dynamically computes the optimal solution for selecting mutation operators required to explore new design regions in hardware. We also address the challenge of inefficient initial input generation by employing PSO-based input generation. Including these optimizations, our final formulation outperforms fuzzers without PSO. Experiments show that PSOFuzz achieves up to 15.25$\times$ speedup for vulnerability detection and up to 2.22$\times$ speedup for coverage compared to the state-of-the-art simulation-based hardware fuzzer.
Abstract
Arising from: Mankowitz, D.J., Michi, A., Zhernov, A. et al. Faster sorting algorithms discovered using deep reinforcement learning.Nature 618, 257-263 (2023). doi.org/10.1038/s41586-023-06004-9. The article cited above presents new implementations of sorting algorithms found through deep reinforcement learning that work on a small number of numeric inputs. For 3 numbers, the published implementation contains 17 assembly instructions, and the authors state that no shorter program exists. This note presents two counterexamples for this claim and a straightforward C/C++ implementation that is faster than theirs.
A Verified Efficient Implementation of the Weighted Path Order
Abstract
The Weighted Path Order of Yamada is a powerful technique for proving termination. It is also supported by CeTA, a certifier for checking untrusted termination proofs. To be more precise, CeTA contains a verified function that computes for two terms whether one of them is larger than the other for a given WPO, i.e., where all parameters of the WPO have been fixed. The problem of this verified function is its exponential runtime in the worst case. Therefore, in this work we develop a polynomial time implementation of WPO that is based on memoization. It also improves upon an earlier verified implementation of the Recursive Path Order: the RPO-implementation uses full terms as keys for the memory, a design which simplified the soundness proofs, but has some runtime overhead. In this work, keys are just numbers, so that the lookup in the memory is faster. Although trivial on paper, this change introduces some challenges for the verification task.
TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
Abstract
Time series forecasting lies at the core of important real-world applications in many fields of science and engineering. The abundance of large time series datasets that consist of complex patterns and long-term dependencies has led to the development of various neural network architectures. Graph neural network approaches, which jointly learn a graph structure based on the correlation of raw values of multivariate time series while forecasting, have recently seen great success. However, such solutions are often costly to train and difficult to scale. In this paper, we propose TimeGNN, a method that learns dynamic temporal graph representations that can capture the evolution of inter-series patterns along with the correlations of multiple series. TimeGNN achieves inference times 4 to 80 times faster than other state-of-the-art graph-based methods while achieving comparable forecasting performance
Lookahead data-gathering strategies for online adaptive model reduction of transport-dominated problems
Authors: Rodrigo Singh, Wayne Isaac Tan Uy, Benjamin Peherstorfer
Subjects: Numerical Analysis (math.NA); Computational Engineering, Finance, and Science (cs.CE)
Abstract
Online adaptive model reduction efficiently reduces numerical models of transport-dominated problems by updating reduced spaces over time, which leads to nonlinear approximations on latent manifolds that can achieve a faster error decay than classical linear model reduction methods that keep reduced spaces fixed. Critical for online adaptive model reduction is coupling the full and reduced model to judiciously gather data from the full model for adapting the reduced spaces so that accurate approximations of the evolving full-model solution fields can be maintained. In this work, we introduce lookahead data-gathering strategies that predict the next state of the full model for adapting reduced spaces towards dynamics that are likely to be seen in the immediate future. Numerical experiments demonstrate that the proposed lookahead strategies lead to accurate reduced models even for problems where previously introduced data-gathering strategies that look back in time fail to provide predictive models. The proposed lookahead strategies also improve the robustness and stability of online adaptive reduced models.
Benchmarking Performance of Deep Learning Model for Material Segmentation on Two HPC Systems
Authors: Warren R. Williams, S. Ross Glandon, Luke L. Morris, Jing-Ru C. Cheng
Abstract
Performance Benchmarking of HPC systems is an ongoing effort that seeks to provide information that will allow for increased performance and improve the job schedulers that manage these systems. We develop a benchmarking tool that utilizes machine learning models and gathers performance data on GPU-accelerated nodes while they perform material segmentation analysis. The benchmark uses a ML model that has been converted from Caffe to PyTorch using the MMdnn toolkit and the MINC-2500 dataset. Performance data is gathered on two ERDC DSRC systems, Onyx and Vulcanite. The data reveals that while Vulcanite has faster model times in a large number of benchmarks, and it is also more subject to some environmental factors that can cause performances slower than Onyx. In contrast the model times from Onyx are consistent across benchmarks.
Abstract
Large language models (LLMs) are now highly capable at a diverse range of tasks. This paper studies whether or not GPT-4, one such LLM, is capable of assisting researchers in the field of adversarial machine learning. As a case study, we evaluate the robustness of AI-Guardian, a recent defense to adversarial examples published at IEEE S&P 2023, a top computer security conference. We completely break this defense: the proposed scheme does not increase robustness compared to an undefended baseline. We write none of the code to attack this model, and instead prompt GPT-4 to implement all attack algorithms following our instructions and guidance. This process was surprisingly effective and efficient, with the language model at times producing code from ambiguous instructions faster than the author of this paper could have done. We conclude by discussing (1) the warning signs present in the evaluation that suggested to us AI-Guardian would be broken, and (2) our experience with designing attacks and performing novel research using the most recent advances in language modeling.
Speeding up Fourier Neural Operators via Mixed Precision
Authors: Colin White, Renbo Tu, Jean Kossaifi, Gennady Pekhimenko, Kamyar Azizzadenesheli, Anima Anandkumar
Abstract
The Fourier neural operator (FNO) is a powerful technique for learning surrogate maps for partial differential equation (PDE) solution operators. For many real-world applications, which often require high-resolution data points, training time and memory usage are significant bottlenecks. While there are mixed-precision training techniques for standard neural networks, those work for real-valued datatypes on finite dimensions and therefore cannot be directly applied to FNO, which crucially operates in the (complex-valued) Fourier domain and in function spaces. On the other hand, since the Fourier transform is already an approximation (due to discretization error), we do not need to perform the operation at full precision. In this work, we (i) profile memory and runtime for FNO with full and mixed-precision training, (ii) conduct a study on the numerical stability of mixed-precision training of FNO, and (iii) devise a training routine which substantially decreases training time and memory usage (up to 34%), with little or no reduction in accuracy, on the Navier-Stokes and Darcy flow equations. Combined with the recently proposed tensorized FNO (Kossaifi et al., 2023), the resulting model has far better performance while also being significantly faster than the original FNO.
Keyword: mobile
Multi-objective Deep Reinforcement Learning for Mobile Edge Computing
Authors: Ning Yang, Junrui Wen, Meng Zhang, Ming Tang
Subjects: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Abstract
Mobile edge computing (MEC) is essential for next-generation mobile network applications that prioritize various performance metrics, including delays and energy consumption. However, conventional single-objective scheduling solutions cannot be directly applied to practical systems in which the preferences of these applications (i.e., the weights of different objectives) are often unknown or challenging to specify in advance. In this study, we address this issue by formulating a multi-objective offloading problem for MEC with multiple edges to minimize expected long-term energy consumption and transmission delay while considering unknown preferences as parameters. To address the challenge of unknown preferences, we design a multi-objective (deep) reinforcement learning (MORL)-based resource scheduling scheme with proximal policy optimization (PPO). In addition, we introduce a well-designed state encoding method for constructing features for multiple edges in MEC systems, a sophisticated reward function for accurately computing the utilities of delay and energy consumption. Simulation results demonstrate that our proposed MORL scheme enhances the hypervolume of the Pareto front by up to 233.1% compared to benchmarks. Our full framework is available at https://github.com/gracefulning/mec_morl_multipolicy.
Space-Air-Ground Integrated Network (SAGIN): A Survey
Authors: Jiming Chen, Han Zhang, Zhe Xie
Subjects: Networking and Internet Architecture (cs.NI); Signal Processing (eess.SP)
Abstract
Since existing mobile communication networks may not be able to meet the low latency and high-efficiency requirements of emerging technologies and applications, novel network architectures need to be investigated to support these new requirements. As a new network architecture that integrates satellite systems, air networks and ground communication, Space-Air-Ground Integrated Network (SAGIN) has attracted extensive attention in recent years. This paper summarizes the recent research work on SAGIN from several aspects, with the basic information of SAGIN first introduced, followed by the physical characteristics. Then the drive and prospects of the current SAGIN architecture in supporting new requirements are deeply analyzed. On this basis, the requirements and challenges are analyzed. Finally, it summarizes the existing solutions and prospects the future research directions.
FLiCR: A Fast and Lightweight LiDAR Point Cloud Compression Based on Lossy RI
Authors: Jin Heo, Christopher Phillips, Ada Gavrilovska
Subjects: Multimedia (cs.MM); Distributed, Parallel, and Cluster Computing (cs.DC)
Abstract
Light detection and ranging (LiDAR) sensors are becoming available on modern mobile devices and provide a 3D sensing capability. This new capability is beneficial for perceptions in various use cases, but it is challenging for resource-constrained mobile devices to use the perceptions in real-time because of their high computational complexity. In this context, edge computing can be used to enable LiDAR online perceptions, but offloading the perceptions on the edge server requires a low-latency, lightweight, and efficient compression due to the large volume of LiDAR point clouds data. This paper presents FLiCR, a fast and lightweight LiDAR point cloud compression method for enabling edge-assisted online perceptions. FLiCR is based on range images (RI) as an intermediate representation (IR), and dictionary coding for compressing RIs. FLiCR achieves its benefits by leveraging lossy RIs, and we show the efficiency of bytestream compression is largely improved with quantization and subsampling. In addition, we identify the limitation of current quality metrics for presenting the entropy of a point cloud, and introduce a new metric that reflects both point-wise and entropy-wise qualities for lossy IRs. The evaluation results show FLiCR is more suitable for edge-assisted real-time perceptions than the existing LiDAR compressions, and we demonstrate the effectiveness of our compression and metric with the evaluations on 3D object detection and LiDAR SLAM.
Keyword: pruning
Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
Authors: Or Sharir, Anima Anandkumar
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL); Machine Learning (stat.ML)
Abstract
Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited. Re-running the model each time is expensive, even with compression techniques like knowledge distillation, pruning, or quantization. Instead, we take an incremental computing approach, looking to reuse calculations as the inputs change. However, the dense connectivity of conventional architectures poses a major obstacle to incremental computation, as even minor input changes cascade through the network and restrict information reuse. To address this, we use vector quantization to discretize intermediate values in the network, which filters out noisy and unnecessary modifications to hidden neurons, facilitating the reuse of their values. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of the modified inputs. Our experiments with adapting the OPT-125M pre-trained language model demonstrate comparable accuracy on document classification while requiring 12.1X (median) fewer operations for processing sequences of atomic edits.
Keyword: diffusion
Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition
Abstract
We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy. For (1), we use a large language model (LLM) to guide high-level planning, and sampling-based robot planners (e.g. motion or grasp samplers) for generating diverse and rich manipulation trajectories. To robustify this data-collection process, the LLM also infers a code-snippet for the success condition of each task, simultaneously enabling the data-collection process to detect failure and retry as well as the automatic labeling of trajectories with success/failure. For (2), we extend the diffusion policy single-task behavior-cloning approach to multi-task settings with language conditioning. Finally, we propose a new multi-task benchmark with 18 tasks across five domains to test long-horizon behavior, common-sense reasoning, tool-use, and intuitive physics. We find that our distilled policy successfully learned the robust retrying behavior in its data collection policy, while improving absolute success rates by 34.8% on average across five domains. The benchmark, code, and qualitative results are on our website https://www.cs.columbia.edu/~huy/scalingup/
Abstract
Augmentation techniques and sampling strategies are crucial in contrastive learning, but in most existing works, augmentation techniques require careful design, and their sampling strategies can only capture a small amount of intrinsic supervision information. Additionally, the existing methods require complex designs to obtain two different representations of the data. To overcome these limitations, we propose a novel framework called the Self-Contrastive Graph Diffusion Network (SCGDN). Our framework consists of two main components: the Attentional Module (AttM) and the Diffusion Module (DiFM). AttM aggregates higher-order structure and feature information to get an excellent embedding, while DiFM balances the state of each node in the graph through Laplacian diffusion learning and allows the cooperative evolution of adjacency and feature information in the graph. Unlike existing methodologies, SCGDN is an augmentation-free approach that avoids "sampling bias" and semantic drift, without the need for pre-training. We conduct a high-quality sampling of samples based on structure and feature information. If two nodes are neighbors, they are considered positive samples of each other. If two disconnected nodes are also unrelated on $k$NN graph, they are considered negative samples for each other. The contrastive objective reasonably uses our proposed sampling strategies, and the redundancy reduction term minimizes redundant information in the embedding and can well retain more discriminative information. In this novel framework, the graph self-contrastive learning paradigm gives expression to a powerful force. SCGDN effectively balances between preserving high-order structure information and avoiding overfitting. The results manifest that SCGDN can consistently generate outperformance over both the contrastive methods and the classical methods.
Imitating Complex Trajectories: Bridging Low-Level Stability and High-Level Behavior
Authors: Adam Block, Daniel Pfrommer, Max Simchowitz
Subjects: Machine Learning (cs.LG); Statistics Theory (math.ST); Machine Learning (stat.ML)
Abstract
We propose a theoretical framework for studying the imitation of stochastic, non-Markovian, potentially multi-modal (i.e. "complex" ) expert demonstrations in nonlinear dynamical systems. Our framework invokes low-level controllers - either learned or implicit in position-command control - to stabilize imitation policies around expert demonstrations. We show that with (a) a suitable low-level stability guarantee and (b) a stochastic continuity property of the learned policy we call "total variation continuity" (TVC), an imitator that accurately estimates actions on the demonstrator's state distribution closely matches the demonstrator's distribution over entire trajectories. We then show that TVC can be ensured with minimal degradation of accuracy by combining a popular data-augmentation regimen with a novel algorithmic trick: adding augmentation noise at execution time. We instantiate our guarantees for policies parameterized by diffusion models and prove that if the learner accurately estimates the score of the (noise-augmented) expert policy, then the distribution of imitator trajectories is close to the demonstrator distribution in a natural optimal transport distance. Our analysis constructs intricate couplings between noise-augmented trajectories, a technique that may be of independent interest. We conclude by empirically validating our algorithmic recommendations.
Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models
Authors: Xin Yuan, Linjie Li, Jianfeng Wang, Zhengyuan Yang, Kevin Lin, Zicheng Liu, Lijuan Wang
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Abstract
In this paper, we study the denoising diffusion probabilistic model (DDPM) in wavelet space, instead of pixel space, for visual synthesis. Considering the wavelet transform represents the image in spatial and frequency domains, we carefully design a novel architecture SFUNet to effectively capture the correlation for both domains. Specifically, in the standard denoising U-Net for pixel data, we supplement the 2D convolutions and spatial-only attention layers with our spatial frequency-aware convolution and attention modules to jointly model the complementary information from spatial and frequency domains in wavelet data. Our new architecture can be used as a drop-in replacement to the pixel-based network and is compatible with the vanilla DDPM training process. By explicitly modeling the wavelet signals, we find our model is able to generate images with higher quality on CIFAR-10, FFHQ, LSUN-Bedroom, and LSUN-Church datasets, than the pixel-based counterpart.
LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement
Authors: Tao Wang, Kaihao Zhang, Ziqian Shao, Wenhan Luo, Bjorn Stenger, Tae-Kyun Kim, Wei Liu, Hongdong Li
Subjects: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
Abstract
Current deep learning methods for low-light image enhancement (LLIE) typically rely on pixel-wise mapping learned from paired data. However, these methods often overlook the importance of considering degradation representations, which can lead to sub-optimal outcomes. In this paper, we address this limitation by proposing a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process, resulting in improved image enhancement. Our proposed degradation-aware learning scheme is based on the understanding that degradation representations play a crucial role in accurately modeling and capturing the specific degradation patterns present in low-light images. To this end, First, a joint learning framework for both image generation and image enhancement is presented to learn the degradation representations. Second, to leverage the learned degradation representations, we develop a Low-Light Diffusion model (LLDiffusion) with a well-designed dynamic diffusion module. This module takes into account both the color map and the latent degradation representations to guide the diffusion process. By incorporating these conditioning factors, the proposed LLDiffusion can effectively enhance low-light images, considering both the inherent degradation patterns and the desired color fidelity. Finally, we evaluate our proposed method on several well-known benchmark datasets, including synthetic and real-world unpaired datasets. Extensive experiments on public benchmarks demonstrate that our LLDiffusion outperforms state-of-the-art LLIE methods both quantitatively and qualitatively. The source code and pre-trained models are available at https://github.com/TaoWangzj/LLDiffusion.
TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis
Authors: Zihan Zhang, Richard Liu, Kfir Aberman, Rana Hanocka
Subjects: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
Abstract
The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain. In this work, we propose to adapt the gradual diffusion concept (operating along a diffusion time-axis) into the temporal-axis of the motion sequence. Our key idea is to extend the DDPM framework to support temporally varying denoising, thereby entangling the two axes. Using our special formulation, we iteratively denoise a motion buffer that contains a set of increasingly-noised poses, which auto-regressively produces an arbitrarily long stream of frames. With a stationary diffusion time-axis, in each diffusion step we increment only the temporal-axis of the motion such that the framework produces a new, clean frame which is removed from the beginning of the buffer, followed by a newly drawn noise vector that is appended to it. This new mechanism paves the way towards a new framework for long-term motion synthesis with applications to character animation and other domains.
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
Authors: Lingdong Kong, Yaru Niu, Shaoyuan Xie, Hanjiang Hu, Lai Xing Ng, Benoit R. Cottereau, Ding Zhao, Liangjun Zhang, Hesheng Wang, Wei Tsang Ooi, Ruijie Zhu, Ziyang Song, Li Liu, Tianzhu Zhang, Jun Yu, Mohan Jing, Pengwei Li, Xiaohua Qi, Cheng Jin, Yingfeng Chen, Jie Hou, Jie Zhang, Zhen Kan, Qiang Ling, Liang Peng, Minglei Li, Di Xu, Changpeng Yang, Yuanqi Yao, Gang Wu, Jian Kuai, Xianming Liu, Junjun Jiang, Jiamian Huang, Baojun Li, Jiale Chen, Shuang Zhang, Sun Ao, Zhenyu Li, Runze Chen, Haiyong Luo, Fang Zhao, Jingze Yu
Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
Abstract
Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website.
Keyword: adaptive
NOMA for STAR-RIS Assisted UAV Networks
Authors: Jiayi Lei, Tiankui Zhang, Xidong Mu, Yuanwei Liu
Subjects: Information Theory (cs.IT); Emerging Technologies (cs.ET); Signal Processing (eess.SP)
Abstract
This paper proposes a novel simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted unmanned aerial vehicle (UAV) non-orthogonal multiple access (NOMA) emergency communication network. Multiple STAR-RISs are deployed to provide additional and intelligent transmission links between trapped users and UAV-mounted base station (BS). Each user selects the nearest STAR-RIS for uploading data, and NOMA is employed for users located at the same side of the same STAR-RIS. Considering piratical requirements of post-disaster emergency communications, we formulate a throughput maximization problem subject to constraints on minimum average rate and maximum energy consumption, where the UAV trajectory, STAR-RIS passive beamforming, and time and power allocation are jointly optimized. Furthermore, we propose a Lagrange based reward constrained proximal policy optimization (LRCPPO) algorithm, which provides an adaptive method for solving the long-term optimization problem with cumulative constraints. Specifically, using Lagrange relaxation, the original problem is transformed into an unconstrained problem with a two-layer structure. The inner layer is solved by penalized reward based proximal policy optimization (PPO) algorithm. In the outer layer, Lagrange multipliers are updated by gradient descent. Numerical results show the proposed algorithm can effectively improve network performance while satisfying the constraints well. It also demonstrates the superiority of the proposed STAR-RIS assisted UAV NOMA network architecture over the benchmark schemes employing reflecting-only RISs and orthogonal multiple access.
Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
Abstract
Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic classes, rendering them unsuitable for medical images due to the scarcity of annotations. To address this challenge, multiple contributions are proposed: First, inspired by spectral decomposition methods, the problem of image decomposition is reframed as a graph partitioning task. The eigenvectors of the Laplacian matrix, derived from the feature affinity matrix of self-supervised networks, are analyzed to estimate the distribution of the objects of interest from the support images. Secondly, we propose a novel self-supervised FSS framework that does not rely on any annotation. Instead, it adaptively estimates the query mask by leveraging the eigenvectors obtained from the support images. This approach eliminates the need for manual annotation, making it particularly suitable for medical images with limited annotated data. Thirdly, to further enhance the decoding of the query image based on the information provided by the support image, we introduce a multi-scale large kernel attention module. By selectively emphasizing relevant features and details, this module improves the segmentation process and contributes to better object delineation. Evaluations on both natural and medical image datasets demonstrate the efficiency and effectiveness of our method. Moreover, the proposed approach is characterized by its generality and model-agnostic nature, allowing for seamless integration with various deep architectures. The code is publicly available at \href{https://github.com/mindflow-institue/annotation_free_fewshot}{\textcolor{magenta}{GitHub}}.
SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting
Authors: Canyu Zhang, Qing Guo, Xiaoguang Li, Renjie Wan, Hongkai Yu, Ivor Tsang, Song Wang
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
In this work, we introduce a challenging image restoration task, referred to as SuperInpaint, which aims to reconstruct missing regions in low-resolution images and generate completed images with arbitrarily higher resolutions. We have found that this task cannot be effectively addressed by stacking state-of-the-art super-resolution and image inpainting methods as they amplify each other's flaws, leading to noticeable artifacts. To overcome these limitations, we propose the detail-enhanced attentional implicit representation (DEAR) that can achieve SuperInpaint with a single model, resulting in high-quality completed images with arbitrary resolutions. Specifically, we use a deep convolutional network to extract the latent embedding of an input image and then enhance the high-frequency components of the latent embedding via an adaptive high-pass filter. This leads to detail-enhanced semantic embedding. We further feed the semantic embedding into an unmask-attentional module that suppresses embeddings from ineffective masked pixels. Additionally, we extract a pixel-wise importance map that indicates which pixels should be used for image reconstruction. Given the coordinates of a pixel we want to reconstruct, we first collect its neighboring pixels in the input image and extract their detail-enhanced semantic embeddings, unmask-attentional semantic embeddings, importance values, and spatial distances to the desired pixel. Then, we feed all the above terms into an implicit representation and generate the color of the specified pixel. To evaluate our method, we extend three existing datasets for this new task and build 18 meaningful baselines using SOTA inpainting and super-resolution methods. Extensive experimental results demonstrate that our method outperforms all existing methods by a significant margin on four widely used metrics.
Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM
Authors: Guillaume Garrigos, Robert M. Gower, Fabian Schaipp
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
Abstract
Here we develop variants of SGD (stochastic gradient descent) with an adaptive step size that make use of the sampled loss values. In particular, we focus on solving a finite sum-of-terms problem, also known as empirical risk minimization. We first detail an idealized adaptive method called $\texttt{SPS}+$ that makes use of the sampled loss values and assumes knowledge of the sampled loss at optimality. This $\texttt{SPS}+$ is a minor modification of the SPS (Stochastic Polyak Stepsize) method, where the step size is enforced to be positive. We then show that $\texttt{SPS}+$ achieves the best known rates of convergence for SGD in the Lipschitz non-smooth. We then move onto to develop $\texttt{FUVAL}$, a variant of $\texttt{SPS}+$ where the loss values at optimality are gradually learned, as opposed to being given. We give three viewpoints of $\texttt{FUVAL}$, as a projection based method, as a variant of the prox-linear method, and then as a particular online SGD method. We then present a convergence analysis of $\texttt{FUVAL}$ and experimental results. The shortcomings of our work is that the convergence analysis of $\texttt{FUVAL}$ shows no advantage over SGD. Another shortcomming is that currently only the full batch version of $\texttt{FUVAL}$ shows a minor advantages of GD (Gradient Descent) in terms of sensitivity to the step size. The stochastic version shows no clear advantage over SGD. We conjecture that large mini-batches are required to make $\texttt{FUVAL}$ competitive. Currently the new $\texttt{FUVAL}$ method studied in this paper does not offer any clear theoretical or practical advantage. We have chosen to make this draft available online nonetheless because of some of the analysis techniques we use, such as the non-smooth analysis of $\texttt{SPS}_+$, and also to show an apparently interesting approach that currently does not work.
Lateral-Direction Localization Attack in High-Level Autonomous Driving: Domain-Specific Defense Opportunity via Lane Detection
Authors: Junjie Shen, Yunpeng Luo, Ziwen Wan, Qi Alfred Chen
Abstract
Localization in high-level Autonomous Driving (AD) systems is highly security critical. While the popular Multi-Sensor Fusion (MSF) based design can be more robust against single-source sensor spoofing attacks, it is found recently that state-of-the-art MSF algorithms is vulnerable to GPS spoofing alone due to practical factors, which can cause various road hazards such as driving off road or onto the wrong way. In this work, we perform the first systematic exploration of the novel usage of lane detection (LD) to defend against such attacks. We first systematically analyze the potentials of such a domain-specific defense opportunity, and then design a novel LD-based defense approach, $LD^3$, that aims at not only detecting such attacks effectively in the real time, but also safely stopping the victim in the ego lane upon detection considering the absence of onboard human drivers. We evaluate $LD^3$ on real-world sensor traces and find that it can achieve effective and timely detection against existing attack with 100% true positive rates and 0% false positive rates. Results also show that $LD^3$ is robust to diverse environmental conditions and is effective at steering the AD vehicle to safely stop within the current traffic lane. We implement $LD^3$ on two open-source high-level AD systems, Baidu Apollo and Autoware, and validate its defense capability in both simulation and the physical world in end-to-end driving. We further conduct adaptive attack evaluations and find that $LD^3$ is effective at bounding the deviations from reaching the attack goals in stealthy attacks and is robust to latest LD-side attack.
Novel BCI paradigm for ALS patients based on EEG and Pupillary Accommodative Response
Abstract
Brain-computer interfaces (BCIs) are one of the few alternatives to enable locked-in syndrome (LIS) patients to communicate with the external world, while they are the only solution for complete locked-in syndrome (CLIS) patients, who lost the ability to control eye movements. However, successful usage of endogenous electroencephalogram(EEG)-based BCI applications is often not trivial, due to EEG variations between and within sessions and long user training required. In this work we suggest an approach to deal with this two main limitations of EEG-BCIs by inserting a progressive and expandable neurofeedback training program, able to continuously tailor the classifier to the specific user, into a multimodal BCI paradigm. We propose indeed the integration of EEG with a non-brain signal: the pupillary accommodative response (PAR). The PAR is a change in pupil size associated with gaze shifts from far to close targets; it is not governed by the somatic nervous system and is thus potentially preserved after the evolution from LIS to CLIS, which often occurs in neurodegenerative diseases, such as amyotrophic lateral sclerosis. Multimodal BCIs have been broadly investigated in literature, due to their ability to yield better overall control performances, but this would be the first attempt combining EEG and PAR. In the context of the BciPar4Sla, we are exploiting these two signals, with the aim of developing a more reliable BCI, adaptive to the extent of evolving together with the user's ability to elicit the brain phenomena needed for optimal control, and providing support even in the transition from LIS to CLIS.
Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation
Authors: Jianan Fan, Dongnan Liu, Hang Chang, Heng Huang, Mei Chen, Weidong Cai
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection. However, they generally operate under the closed-set adaptation setting assuming an identical label set between the source and target domains, which is over-restrictive in clinical practice where new classes commonly exist across datasets due to taxonomic inconsistency. While several methods have been presented to tackle both domain shifts and incoherent label sets, none of them take into account the common characteristics of the two issues and consider the learning dynamics along network training. In this work, we propose optimization trajectory distillation, a unified approach to address the two technical challenges from a new perspective. It exploits the low-rank nature of gradient space and devises a dual-stream distillation algorithm to regularize the learning dynamics of insufficiently annotated domain and classes with the external guidance obtained from reliable sources. Our approach resolves the issue of inadequate navigation along network optimization, which is the major obstacle in the taxonomy adaptive cross-domain adaptation scenario. We evaluate the proposed method extensively on several tasks towards various endpoints with clinical and open-world significance. The results demonstrate its effectiveness and improvements over previous methods.
EFLNet: Enhancing Feature Learning for Infrared Small Target Detection
Authors: Bo Yang, Xinyu Zhang, Jiahao Zhu, Jian Zhang, Dongjian Tian, Jun Luo, Mingliang Zhou, Yangjun Pi
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Single-frame infrared small target detection is considered to be a challenging task, due to the extreme imbalance between target and background, bounding box regression is extremely sensitive to infrared small targets, and small target information is easy to lose in the high-level semantic layer. In this paper, we propose an enhancing feature learning network (EFLNet) based on YOLOv7 framework to solve these problems. First, we notice that there is an extremely imbalance between the target and the background in the infrared image, which makes the model pay more attention to the background features, resulting in missed detection. To address this problem, we propose a new adaptive threshold focal loss function that adjusts the loss weight automatically, compelling the model to allocate greater attention to target features. Second, we introduce the normalized Gaussian Wasserstein distance to alleviate the difficulty of model convergence caused by the extreme sensitivity of the bounding box regression to infrared small targets. Finally, we incorporate a dynamic head mechanism into the network to enable adaptive learning of the relative importance of each semantic layer. Experimental results demonstrate our method can achieve better performance in the detection performance of infrared small targets compared to state-of-the-art deep-learning based methods.
Turning Whisper into Real-Time Transcription System
Abstract
Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we build on top of Whisper and create Whisper-Streaming, an implementation of real-time speech transcription and translation of Whisper-like models. Whisper-Streaming uses local agreement policy with self-adaptive latency to enable streaming transcription. We show that Whisper-Streaming achieves high quality and 3.3 seconds latency on unsegmented long-form speech transcription test set, and we demonstrate its robustness and practical usability as a component in live transcription service at a multilingual conference.
Lookahead data-gathering strategies for online adaptive model reduction of transport-dominated problems
Authors: Rodrigo Singh, Wayne Isaac Tan Uy, Benjamin Peherstorfer
Subjects: Numerical Analysis (math.NA); Computational Engineering, Finance, and Science (cs.CE)
Abstract
Online adaptive model reduction efficiently reduces numerical models of transport-dominated problems by updating reduced spaces over time, which leads to nonlinear approximations on latent manifolds that can achieve a faster error decay than classical linear model reduction methods that keep reduced spaces fixed. Critical for online adaptive model reduction is coupling the full and reduced model to judiciously gather data from the full model for adapting the reduced spaces so that accurate approximations of the evolving full-model solution fields can be maintained. In this work, we introduce lookahead data-gathering strategies that predict the next state of the full model for adapting reduced spaces towards dynamics that are likely to be seen in the immediate future. Numerical experiments demonstrate that the proposed lookahead strategies lead to accurate reduced models even for problems where previously introduced data-gathering strategies that look back in time fail to provide predictive models. The proposed lookahead strategies also improve the robustness and stability of online adaptive reduced models.
A Self-Adaptive Penalty Method for Integrating Prior Knowledge Constraints into Neural ODEs
Authors: C. Coelho, M. Fernanda P. Costa, L. L. Ferrás
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
Abstract
The continuous dynamics of natural systems has been effectively modelled using Neural Ordinary Differential Equations (Neural ODEs). However, for accurate and meaningful predictions, it is crucial that the models follow the underlying rules or laws that govern these systems. In this work, we propose a self-adaptive penalty algorithm for Neural ODEs to enable modelling of constrained natural systems. The proposed self-adaptive penalty function can dynamically adjust the penalty parameters. The explicit introduction of prior knowledge helps to increase the interpretability of Neural ODE -based models. We validate the proposed approach by modelling three natural systems with prior knowledge constraints: population growth, chemical reaction evolution, and damped harmonic oscillator motion. The numerical experiments and a comparison with other penalty Neural ODE approaches and \emph{vanilla} Neural ODE, demonstrate the effectiveness of the proposed self-adaptive penalty algorithm for Neural ODEs in modelling constrained natural systems. Moreover, the self-adaptive penalty approach provides more accurate and robust models with reliable and meaningful predictions.
Adaptive Segmentation Network for Scene Text Detection
Authors: Guiqin Zhao
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Inspired by deep convolution segmentation algorithms, scene text detectors break the performance ceiling of datasets steadily. However, these methods often encounter threshold selection bottlenecks and have poor performance on text instances with extreme aspect ratios. In this paper, we propose to automatically learn the discriminate segmentation threshold, which distinguishes text pixels from background pixels for segmentation-based scene text detectors and then further reduces the time-consuming manual parameter adjustment. Besides, we design a Global-information Enhanced Feature Pyramid Network (GE-FPN) for capturing text instances with macro size and extreme aspect ratios. Following the GE-FPN, we introduce a cascade optimization structure to further refine the text instances. Finally, together with the proposed threshold learning strategy and text detection structure, we design an Adaptive Segmentation Network (ASNet) for scene text detection. Extensive experiments are carried out to demonstrate that the proposed ASNet can achieve the state-of-the-art performance on four text detection benchmarks, i.e., ICDAR 2015, MSRA-TD500, ICDAR 2017 MLT and CTW1500. The ablation experiments also verify the effectiveness of our contributions.
Keyword: quantization
Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
Authors: Or Sharir, Anima Anandkumar
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL); Machine Learning (stat.ML)
Abstract
Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited. Re-running the model each time is expensive, even with compression techniques like knowledge distillation, pruning, or quantization. Instead, we take an incremental computing approach, looking to reuse calculations as the inputs change. However, the dense connectivity of conventional architectures poses a major obstacle to incremental computation, as even minor input changes cascade through the network and restrict information reuse. To address this, we use vector quantization to discretize intermediate values in the network, which filters out noisy and unnecessary modifications to hidden neurons, facilitating the reuse of their values. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of the modified inputs. Our experiments with adapting the OPT-125M pre-trained language model demonstrate comparable accuracy on document classification while requiring 12.1X (median) fewer operations for processing sequences of atomic edits.
FLiCR: A Fast and Lightweight LiDAR Point Cloud Compression Based on Lossy RI
Authors: Jin Heo, Christopher Phillips, Ada Gavrilovska
Subjects: Multimedia (cs.MM); Distributed, Parallel, and Cluster Computing (cs.DC)
Abstract
Light detection and ranging (LiDAR) sensors are becoming available on modern mobile devices and provide a 3D sensing capability. This new capability is beneficial for perceptions in various use cases, but it is challenging for resource-constrained mobile devices to use the perceptions in real-time because of their high computational complexity. In this context, edge computing can be used to enable LiDAR online perceptions, but offloading the perceptions on the edge server requires a low-latency, lightweight, and efficient compression due to the large volume of LiDAR point clouds data. This paper presents FLiCR, a fast and lightweight LiDAR point cloud compression method for enabling edge-assisted online perceptions. FLiCR is based on range images (RI) as an intermediate representation (IR), and dictionary coding for compressing RIs. FLiCR achieves its benefits by leveraging lossy RIs, and we show the efficiency of bytestream compression is largely improved with quantization and subsampling. In addition, we identify the limitation of current quality metrics for presenting the entropy of a point cloud, and introduce a new metric that reflects both point-wise and entropy-wise qualities for lossy IRs. The evaluation results show FLiCR is more suitable for edge-assisted real-time perceptions than the existing LiDAR compressions, and we demonstrate the effectiveness of our compression and metric with the evaluations on 3D object detection and LiDAR SLAM.
Keyword: efficient
Explainable Disparity Compensation for Efficient Fair Ranking
Forecasting, capturing and activation of carbon-dioxide (CO$_2$): Integration of Time Series Analysis, Machine Learning, and Material Design
DBGSA: A Novel Data Adaptive Bregman Clustering Algorithm
Domain preserving and strongly converging explicit scheme for the stochastic SIS epidemic model
Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models
A grid-overlay finite difference method for the fractional Laplacian on arbitrary bounded domains
Integrating Offline Reinforcement Learning with Transformers for Sequential Recommendation
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
Single Channel Speech Enhancement Using U-Net Spiking Neural Networks
PSOFuzz: Fuzzing Processors with Particle Swarm Optimization
Technical note: ShinyAnimalCV: open-source cloud-based web application for object detection, segmentation, and three-dimensional visualization of animals using computer vision
SPICE Modeling of Memcomputing Logic Gates
Open Problems in Computer Vision for Wilderness SAR and The Search for Patricia Wu-Murad
Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum
Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition
Speed Reading Tool Powered by Artificial Intelligence for Students with ADHD, Dyslexia, or Short Attention Span
Adversarial Sleeping Bandit Problems with Multiple Plays: Algorithm and Ranking Application
Limiting Moments of Autocorrelation Demerit Factors of Binary Sequences
HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting
TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
Metric-Based In-context Learning: A Case Study in Text Simplification
The Unweighted and Weighted Reverse Shortest Path Problem for Disk Graphs
Fuzzy order-sorted feature logic
Prediction of wind turbines power with physics-informed neural networks and evidential uncertainty quantification
Quinpi: Integrating stiff hyperbolic systems with implicit high order finite volume schemes
Singularity Distance Computations of 3-RPR Manipulators Using Intrinsic Metrics
New Interaction Paradigm for Complex EDA Software Leveraging GPT
Semantic Image Completion and Enhancement using GANs
Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation
Fair Machine Unlearning: Data Removal while Mitigating Disparities
SPC5: an efficient SpMV framework vectorized using ARM SVE and x86 AVX-512
MATNilm: Multi-appliance-task Non-intrusive Load Monitoring with Limited Labeled Data
Contrastive Knowledge Amalgamation for Unsupervised Image Classification
Likely, Light, and Accurate Context-Free Clusters-based Trajectory Prediction
A Differential Datalog Interpreter
DNN-MG: A Hybrid Neural Network/Finite Element Method with Applications to 3D Simulations of the Navier-Stokes Equations
ArcGPT: A Large Language Model Tailored for Real-world Archival Applications
Lookahead data-gathering strategies for online adaptive model reduction of transport-dominated problems
Knot Theory and Error-Correcting Codes
Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving
Text-guided Foundation Model Adaptation for Pathological Image Classification
GET3D--: Learning GET3D from Unconstrained Image Collections
Solving Data Quality Problems with Desbordante: a Demo
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
Efficient Interaction-Aware Interval Analysis of Neural Network Feedback Loops
A localized orthogonal decomposition strategy for hybrid discontinuous Galerkin methods
Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
Scaling TransNormer to 175 Billion Parameters
Gzip versus bag-of-words for text classification with KNN
FLiCR: A Fast and Lightweight LiDAR Point Cloud Compression Based on Lossy RI
A LLM Assisted Exploitation of AI-Guardian
Samplable Anonymous Aggregation for Private Federated Data Analysis
A Sparse Quantized Hopfield Network for Online-Continual Memory
Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
Keyword: faster
Hypergraph Isomorphism Computation
PSOFuzz: Fuzzing Processors with Particle Swarm Optimization
Shorter and faster than Sort3AlphaDev
A Verified Efficient Implementation of the Weighted Path Order
TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
Lookahead data-gathering strategies for online adaptive model reduction of transport-dominated problems
Benchmarking Performance of Deep Learning Model for Material Segmentation on Two HPC Systems
A LLM Assisted Exploitation of AI-Guardian
Speeding up Fourier Neural Operators via Mixed Precision
Keyword: mobile
Multi-objective Deep Reinforcement Learning for Mobile Edge Computing
Space-Air-Ground Integrated Network (SAGIN): A Survey
FLiCR: A Fast and Lightweight LiDAR Point Cloud Compression Based on Lossy RI
Keyword: pruning
Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
Keyword: diffusion
Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition
Self-Contrastive Graph Diffusion Network
Imitating Complex Trajectories: Bridging Low-Level Stability and High-Level Behavior
Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models
LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement
TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
Keyword: adaptive
NOMA for STAR-RIS Assisted UAV Networks
Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting
Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM
Lateral-Direction Localization Attack in High-Level Autonomous Driving: Domain-Specific Defense Opportunity via Lane Detection
Novel BCI paradigm for ALS patients based on EEG and Pupillary Accommodative Response
Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation
EFLNet: Enhancing Feature Learning for Infrared Small Target Detection
Turning Whisper into Real-Time Transcription System
Lookahead data-gathering strategies for online adaptive model reduction of transport-dominated problems
A Self-Adaptive Penalty Method for Integrating Prior Knowledge Constraints into Neural ODEs
Adaptive Segmentation Network for Scene Text Detection
Keyword: quantization
Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
FLiCR: A Fast and Lightweight LiDAR Point Cloud Compression Based on Lossy RI