GANExplainer: GAN-based Graph Neural Networks Explainer

TL;DR

GANExplainer introduces a GAN-based approach to improve the accuracy of explanations for graph neural networks, significantly outperforming existing methods on synthetic datasets.

Contribution

The paper presents GANExplainer, a novel GAN-based framework that enhances explanation accuracy for GNNs, addressing limitations of previous explainers.

Findings

GANExplainer improves explanation accuracy by up to 35% on synthetic datasets.

It outperforms existing state-of-the-art GNN explainers.

The approach demonstrates the effectiveness of GAN architectures in GNN explainability.

Abstract

With the rapid deployment of graph neural networks (GNNs) based techniques into a wide range of applications such as link prediction, node classification, and graph classification the explainability of GNNs has become an indispensable component for predictive and trustworthy decision-making. Thus, it is critical to explain why graph neural network (GNN) makes particular predictions for them to be believed in many applications. Some GNNs explainers have been proposed recently. However, they lack to generate accurate and real explanations. To mitigate these limitations, we propose GANExplainer, based on Generative Adversarial Network (GAN) architecture. GANExplainer is composed of a generator to create explanations and a discriminator to assist with the Generator development. We investigate the explanation accuracy of our models by comparing the performance of GANExplainer with other state-of-the-art methods. Our empirical results on synthetic datasets indicate that GANExplainer improves explanation accuracy by up to 35\% compared to its alternatives.