-
My suggestion is about project Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective. The current cuda version seems not that easy for a fast verification due to unexpected comp…
-
#121
CORL, DAG-GNN, and other methods only return and thresh comparison of 0-1 matrix, which CORL thresh is the algorithm comes with 0.3 can not be changed, but a lot of datasets with 0.3 is not acc…
-
Hello,
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-tracking prob…
-
Hello,
Thank you for your great work, I managed to run the code with the provided dataset.
However, I have been exploring the repository as well as the paper and noticed that the method for prepar…
-
Hello,
Thank you for developing and sharing a unique algorithm for sequence embedding.
I am currently implementing your SGT algorithm for protein embedding.
While reading your paper, I could see …
-
Hi authors, the GNN reranking is fast, great work! And I would like to expand it from just ranking to distance calculation, and I modified the code by removing the reranking and only keeping cosine si…
-
## 🚀 Feature
RAPIDS cuGraph is a high-quality library for GPU accelerated graph algorithms (see the [full list of supported algorithms](https://github.com/rapidsai/cugraph#supported-algorithms)).…
-
### 🐛 Describe the bug
Hi! The new explainer interface fails when we have more than one relation type with the FiLMConv layer:
```
from torch_geometric.explain import Explainer, CaptumExplainer
…
-
What is the best way to use gCastle on mixed type data, so for datasets with a combination of numerical and categorical (nominal and/of ordinal)?
Is any of the causal discovery algorithms specifical…
-
Thank you for your great repo!
I've used this package in nearly all of my projects. Gradually, I found that the most urgent and useful feature will be a nested argument parser. That is:
```bash
…