pyg-team/pytorch_geometric

Add `EGT` to `nn.conv`

Open

#8,258 opened on Oct 24, 2023

View on GitHub
 (0 comments) (2 reactions) (0 assignees)Python (19,985 stars) (3,514 forks)batch import
featuregood first issuehelp wanted

Description

🚀 The feature, motivation and pitch

Global Self-Attention as a Replacement for Graph Convolution

Alternatives

No response

Additional context

No response

Contributor guide

Tech stack
pythonpytorch
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
PyTorch basicsPyTorch GeometricGraph neural networksTransformer architectures
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25
Research direction
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.