Loading...
Reliable and faithful generative explainers for graph neural networks
Li, Yiqiao Zhou, Jianlong Zheng, Boyuan Shafiabady, Niusha Chen, Fang
Li, Yiqiao
Zhou, Jianlong
Zheng, Boyuan
Shafiabady, Niusha
Chen, Fang
Abstract
Graph neural networks (GNNs) have been effectively implemented in a variety of real-world applications, although their underlying work mechanisms remain a mystery. To unveil this mystery and advocate for trustworthy decision-making, many GNN explainers have been proposed. However, existing explainers often face significant challenges, such as the following: (1) explanations being tied to specific instances; (2) limited generalisability to unseen graphs; (3) potential generation of invalid graph structures; and (4) restrictions to particular tasks (e.g., node classification, graph classification). To address these challenges, we propose a novel explainer, GAN-GNNExplainer, which employs a generator to produce explanations and a discriminator to oversee the generation process, enhancing the reliability of the outputs. Despite its advantages, GAN-GNNExplainer still struggles with generating faithful explanations and underperforms on real-world datasets. To overcome these shortcomings, we introduce ACGAN-GNNExplainer, an approach that improves upon GAN-GNNExplainer by using a more robust discriminator that consistently monitors the generation process, thereby producing explanations that are both reliable and faithful. Extensive experiments on both synthetic and real-world graph datasets demonstrate the superiority of our proposed methods over existing GNN explainers.
Keywords
graph neural networks, explanations, generative methods, faithful, reliable
Date
2024
Type
Journal article
Journal
Machine Learning and Knowledge Extraction
Book
Volume
6
Issue
4
Page Range
2913-2929
Article Number
ACU Department
Peter Faber Business School
Faculty of Law and Business
Faculty of Law and Business
Collections
Relation URI
Source URL
Event URL
Open Access Status
Published as ‘gold’ (paid) open access
License
CC BY 4.0
File Access
Open
Notes
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).