Quan (Andy) Gan

## 🚀 Feature Support neighbor sampling without neighbor deduplication, examples including TGATSampler and KGCNSampler. ## Motivation The current neighbor sampling implementation by default will deduplicate the neighbors after sampling to...

Allow overriding of existing functional APIs on DataPipe subclasses

1

### 🚀 The feature Allow users to override existing functional APIs on their own DataPipe subclasses. ### Motivation, pitch Consider the use case where I iterate over a tensor in...

Recommended practice to shuffle data with datapipes differently every epoch

4

### 📚 The doc issue I was trying `torchdata` 0.4.0 and I found that shuffling with data pipes will always yield the same result across different epochs, unless I shuffle...

Stuck at evaluation after submitting to node classification leaderboard （节点预测提交后没有返回评测结果）

1

After I made a submission to node classification leaderboard, the interface is stuck at 100% upload and a greyed-out "Evaluating" button forever without returning any results. Is there any issue...

[Sampling] Sampling with edge masks

16

## Description This PR extends the `prob` argument of `sample_neighbors` to accept a boolean tensor to represent which edges are eligible for sampling. It also adds a `mask` argument to...

[Refactor?] Clean up and document the utility function usages

3

## 🚀 Feature (This is not really a "feature" request, but more like a code organization and refactor request) Clean up, organize, and document all the internal utility functions DGL...

[DataLoader] Allow batch_size=None for GraphDataLoader

9

Fixes #3358.

## 🔨Work Item **IMPORTANT:** * This template is only for dev team to track project progress. For feature request or bug report, please use the corresponding issue templates. * DO...

[CI] Testing DGL build under different CUDA/CMake configurations

2

We are missing a lot of unit/nightly tests, particularly under different build settings. This include: * Different CUDA versions * `-DBUILD_TORCH=ON|OFF` (related: #4450 ) * Windows GPU tests * Linux...

Consider three atoms `A -- B -- C`, where `A` and `B` are connected within the same clique `C1`, and `B` and `C` are connected but belonging to different cliques...