pyg-team/pytorch_geometric

Add `KerGNN` to `conv.nn` as layer type

Open

#4,937 opened on Jul 7, 2022

View on GitHub
 (4 comments) (0 reactions) (0 assignees)Python (3,514 forks)batch import
0 - Priority P0featurehelp wantednn

Repository metrics

Stars
 (19,985 stars)
PR merge metrics
 (Avg merge 35d 1h) (14 merged PRs in 30d)

Description

🚀 The feature, motivation and pitch

Dear PyTorch-Geometric team, dear Matthias,

stumbled upon this novel GNN layer type idea named KerGNN, and it worked out quite well in their and my own experiments for different occasions. Their code is available at https://github.com/asFeng/kergnns, while being directly compatible to your library, i.e. using PyTorch and immanently compatible to your dataset formulations.

Best wishes, Tilman

Alternatives

No response

Additional context

No response

Contributor guide

Research direction
Read the KerGNN paper and the provided reference implementation, then integrate it into the conv.nn module following PyTorch Geometric's conventions.
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.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorchGraph Neural Networks
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40