fix(inductive): graph dict support + prune multiclass s4vm/tsvm configs #30
Conversation
![github-code-quality[bot]](https://avatars.githubusercontent.com/u/9919?s=60&v=4){kind=small}
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
ModSSC/src/modssc/inductive/methods/deep_utils.py
Lines 229 to 233 in cb3711d
Normalize slice indices before subgraph
slice_data forwards idx directly into torch_geometric.utils.subgraph, but several call sites pass slice(...) (e.g., ADSH _update_scores and TriNet batching). subgraph expects a tensor/list/mask subset, so a Python slice will raise a TypeError, which means graph dict inputs with edge_index will crash as soon as slice-based batching runs. Converting slices to an index tensor (e.g., torch.arange(start, end, device=...)) before calling subgraph avoids this failure.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
1 participant
Summary
What does this PR change?
Checklist
Notes
Anything reviewers should know?