pyg-team/pytorch_geometric

Add `EGT` to `nn.conv`

Open

#8,258 建立於 2023年10月24日

在 GitHub 查看
 (0 留言) (2 反應) (0 負責人)Python (19,985 star) (3,514 fork)batch import
featuregood first issuehelp wanted

描述

🚀 The feature, motivation and pitch

Global Self-Attention as a Replacement for Graph Convolution

Alternatives

No response

Additional context

No response

貢獻者指南

技術棧
pythonpytorch
領域
machine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
3-5 days
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
fresh
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
PyTorch basicsPyTorch GeometricGraph neural networksTransformer architectures
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
25
研究方向
Implement the EGT (Edge Graph Transformer) convolution as described in the paper 'Global Self Attention as a Replacement for Graph Convolution'. Study existing convolution implementations in PyTorch Geometric's nn.conv module, such as GCNConv and GATConv, to understand the pattern. Focus on adapting the self attention mechanism to graph edges. Since there are no comments or PRs, the implementation should be self contained and test against standard benchmarks.