/GNNs

Graph Neural Network layers implementation & spectral graph theory.

Primary LanguageJupyter Notebook

Graph Neural Network

This repository provides a Tensorflow 2 implementation of some GNN layers using tf.keras.layers.Layer subclassing, as well a notebook to evaluate their expressive power through an image filtering task.

Spatial Graph Convolution

The general framework for spatial graph convolution (message passing) is :

A GNN layer can be defined by different C matrices. For now, this project contains :

  • Simple GNN :
  • Vanilla GNN :
  • General GNN :
  • GIN

References

Muhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, Paul Honeine. Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective. ICLR 2021.