ACGAN-GNNExplainer : Auxiliary conditional generative explainer for graph neural networks
Conference paper
Li, Yiqiao, Zhou, Jianlong, Dong, Yifei, Shafiabady, Niusha and Chen, Fang. (2023). ACGAN-GNNExplainer : Auxiliary conditional generative explainer for graph neural networks. 32nd ACM International Conference on Information and Knowledge Management (CIKM ’23). Birmingham, United Kingdom 21 - 25 Oct 2023 Association for Computing Machinery. pp. 1259-1267 https://doi.org/10.1145/3583780.3614772
Authors | Li, Yiqiao, Zhou, Jianlong, Dong, Yifei, Shafiabady, Niusha and Chen, Fang |
---|---|
Type | Conference paper |
Abstract | Graph neural networks (GNNs) have proven their efficacy in a variety of real-world applications, but their underlying mechanisms remain a mystery. To address this challenge and enable reliable decision-making, many GNN explainers have been proposed in recent years. However, these methods often encounter limitations, including their dependence on specific instances, lack of generalizability to unseen graphs, producing potentially invalid explanations, and yielding inadequate fidelity. To overcome these limitations, we, in this paper, introduce the Auxiliary Classifier Generative Adversarial Network (ACGAN) into the field of GNN explanation and propose a new GNN explainer dubbed ACGAN-GNNExplainer. Our approach leverages a generator to produce explanations for the original input graphs while incorporating a discriminator to oversee the generation process, ensuring explanation fidelity and improving accuracy. Experimental evaluations conducted on both synthetic and real-world graph datasets demonstrate the superiority of our proposed method compared to other existing GNN explainers. |
Keywords | graph neural networks; explanations; graph neural network explainer; conditional generative adversarial network |
Year | 2023 |
Publisher | Association for Computing Machinery |
Digital Object Identifier (DOI) | https://doi.org/10.1145/3583780.3614772 |
Publisher's version | License All rights reserved File Access Level Controlled |
Book title | CIKM ’23 : Proceedings of the 32nd ACM International Conference on Information and Knowledge Management |
Page range | 1259-1267 |
ISBN | 9798400701245 |
Web address (URL) of conference proceedings | https://doi.org/10.1145/3583780 |
Output status | Published |
Publication dates | |
Online | 21 Oct 2023 |
Publication process dates | |
Deposited | 28 May 2025 |
Additional information | © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. |
https://acuresearchbank.acu.edu.au/item/91x93/acgan-gnnexplainer-auxiliary-conditional-generative-explainer-for-graph-neural-networks
Restricted files
Publisher's version
4
total views0
total downloads0
views this month0
downloads this month