-
I saw your work at ICML2022 and was very interested in it. When I tried to test it at resnet50, I found that there was a significant drop in training accuracy after training the same epoch using GACT.…
-
Hello Robert,
Let me start by saying that I am a fan of your work here. I have recently open-sourced by GNN-based meta-learning method for optimization. I have applied it to the sparse index-tracki…
-
### News
- Conference
- NeurIPS 2022: Rebuttal & Author-Reviewer Period
- AAAI 2023: ABS 8.8 (AoE), Full 8.15 (AoE)
- KCCV 2022: 8월 8일 ~ 10일 코엑스 오디토리움
- [AI만든 정책을 중심으로 한 정당이 의회선거에? 덴마크…
-
Dear Zhang,
I am now running the experiments from your code. I get the embedding representation and then compute l2 distance as the kernel for node classification and link prediction, but it is poo…
ghost updated
2 years ago
-
Hello,
I was wondering if someone could point me towards some publicly available dataset(s) of minigrid navigation environments?
I am looking for the simplest navigation task specification with …
-
请问现在graph-learn是否支持spark分布式训练？多机多GPU分布式训练？
是否支持TransformerConv，KGCN等较新的算法？
egograph是否可以对接pyg，或者像subgraph那样通过GSL转换数据集从而支持pyg?
训练/预测时各个点是独立训练的么，除了需要共享参数？
每个点维护自身的k跳邻居信息，这种做法是否会导致较大的内存开销？（是否有量化的统计数据）…
-
## 🚀 Feature
Replace std::default_random_engine with a better proven PRNG that passes statistical tests.
## Motivation
I noticed that the DGL PRNG is just STL default random engine, which is …
-
Thank you for this wonderful work. The detailed descriptions of several baseline methods cannot be found in the paper, nor in the code here. Could you please provide the code or detailed explanation f…
-
Hi,
I was trying to run the SUREL algorithm with a GNN `Net` model. However, I could not see any GNN model architecture being supported in `models.py`/`layers.py` file. Could you please let me know…
-
## 🚀 Feature
[This](https://arxiv.org/abs/2002.09518) papers proposes a new graph convolution/coarsening algorithm. The convolution layer doesn't use any kind of gnn, i.e it doesn't explicitly use th…
wsad1 updated
2 years ago