Explainability Techniques for Graph Convolutional Networks

Code

• github.com/baldassarreFe/graph-network-explainability
  OfficialIn paperpytorch★ 0
• github.com/xiaomingaaa/GNNApp-Papers
  none★ 0

Abstract

Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them. In this work, we study the explainability of Graph Network decisions using two main classes of techniques, gradient-based and decomposition-based, on a toy dataset and a chemistry task. Our study sets the ground for future development as well as application to real-world problems.

Reproductions