Graph-based Integrated Gradients for Explaining Graph Neural Networks
Machine Learning
2025-09-10 v1
Abstract
Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to graphs. We demonstrate on four synthetic datasets that GB-IG accurately identifies crucial structural components of the graph used in classification tasks. We further demonstrate on three prevalent real-world graph datasets that GB-IG outperforms IG in highlighting important features for node classification tasks.
Cite
@article{arxiv.2509.07648,
title = {Graph-based Integrated Gradients for Explaining Graph Neural Networks},
author = {Lachlan Simpson and Kyle Millar and Adriel Cheng and Cheng-Chew Lim and Hong Gunn Chew},
journal= {arXiv preprint arXiv:2509.07648},
year = {2025}
}
Comments
Accepted at the Australasian Joint Conference on Artificial Intelligence (AJCAI) 2025