ACGAN-GNNExplainer: Auxiliary Conditional Generative Explainer for Graph Neural Networks

TL;DR

This paper introduces ACGAN-GNNExplainer, a novel method that uses generative adversarial networks to produce more accurate, generalizable, and valid explanations for graph neural networks, addressing limitations of previous explainers.

Contribution

The paper presents a new GNN explainer leveraging ACGAN to enhance explanation fidelity, validity, and generalizability across unseen graphs.

Findings

Outperforms existing GNN explainers on synthetic datasets

Achieves higher explanation fidelity and validity

Demonstrates robustness on real-world graph datasets

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~\emph{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.