Demystifying Graph Neural Network Explanations

TL;DR

This paper critically examines existing perturbation-based explanation methods for graph neural networks, identifying common pitfalls in data, evaluation, and presentation, and proposes remedies through an empirical study.

Contribution

It provides a comprehensive analysis of current GNN explanation approaches, highlighting issues and offering solutions to improve explanation quality and evaluation.

Findings

Identified key pitfalls in synthetic data generation for GNN explanations

Highlighted shortcomings in current evaluation metrics

Proposed remedies to improve explanation clarity and reliability

Abstract

Graph neural networks (GNNs) are quickly becoming the standard approach for learning on graph structured data across several domains, but they lack transparency in their decision-making. Several perturbation-based approaches have been developed to provide insights into the decision making process of GNNs. As this is an early research area, the methods and data used to evaluate the generated explanations lack maturity. We explore these existing approaches and identify common pitfalls in three main areas: (1) synthetic data generation process, (2) evaluation metrics, and (3) the final presentation of the explanation. For this purpose, we perform an empirical study to explore these pitfalls along with their unintended consequences and propose remedies to mitigate their effects.