Add `EGT` to `nn.conv`

描述

贡献者指南

技术栈

pythonpytorch

领域

machine learning

议题类型

feature

难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。

4

预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。

3-5 days

活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。

fresh

清晰度议题是否清楚说明期望改动、验收标准和下一步。

mostly clear

前置要求

PyTorch basicsPyTorch GeometricGraph neural networksTransformer architectures

新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。

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.