Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods

TL;DR

This paper provides the first comprehensive theoretical and empirical analysis of the reliability of GNN explanation methods, evaluating their faithfulness, stability, and fairness across multiple datasets.

Contribution

It introduces a rigorous theoretical framework for analyzing GNN explainers and validates these insights through extensive experiments on real-world data.

Findings

Theoretical bounds on explanation property violations

Empirical validation of explanation method behaviors

Insights into reliability and limitations of GNN explainers

Abstract

As Graph Neural Networks (GNNs) are increasingly being employed in critical real-world applications, several methods have been proposed in recent literature to explain the predictions of these models. However, there has been little to no work on systematically analyzing the reliability of these methods. Here, we introduce the first-ever theoretical analysis of the reliability of state-of-the-art GNN explanation methods. More specifically, we theoretically analyze the behavior of various state-of-the-art GNN explanation methods with respect to several desirable properties (e.g., faithfulness, stability, and fairness preservation) and establish upper bounds on the violation of these properties. We also empirically validate our theoretical results using extensive experimentation with nine real-world graph datasets. Our empirical results further shed light on several interesting insights about the behavior of state-of-the-art GNN explanation methods.