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

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.

References in corpus (9)

• Conditional Generative Adversarial Nets
• Graph Neural Network for Traffic Forecasting: A Survey
• CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
• XGNN: Towards Model-Level Explanations of Graph Neural Networks
• Parameterized Explainer for Graph Neural Network
• Fully Automatic Electrocardiogram Classification System based on Generative Adversarial Network with Auxiliary Classifier
• CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks
• Robust Counterfactual Explanations on Graph Neural Networks
• A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics