Saved in:
Bibliographic Details
Main Authors: Simpson, Lachlan, Millar, Kyle, Cheng, Adriel, Lim, Cheng-Chew, Chew, Hong Gunn
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.07648
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909778914050048
author Simpson, Lachlan
Millar, Kyle
Cheng, Adriel
Lim, Cheng-Chew
Chew, Hong Gunn
author_facet Simpson, Lachlan
Millar, Kyle
Cheng, Adriel
Lim, Cheng-Chew
Chew, Hong Gunn
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07648
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph-based Integrated Gradients for Explaining Graph Neural Networks
Simpson, Lachlan
Millar, Kyle
Cheng, Adriel
Lim, Cheng-Chew
Chew, Hong Gunn
Machine Learning
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.
title Graph-based Integrated Gradients for Explaining Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2509.07648