Explainability in subgraphs-enhanced Graph Neural Networks

TL;DR

This paper adapts PGExplainer to subgraphs-enhanced GNNs, enabling interpretable explanations of their predictions by accounting for subgraph contributions, validated through experiments on real and synthetic datasets.

Contribution

It introduces a novel explainability framework for SGNNs by modifying PGExplainer to handle subgraph contributions, improving interpretability of complex GNN models.

Findings

Successful explanation of SGNN decisions on graph classification tasks

Framework produces human-interpretable explanations

Effective on both real and synthetic datasets

Abstract

Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been introduced to enhance the expressive power of Graph Neural Networks (GNNs), which was proved to be not higher than the 1-dimensional Weisfeiler-Leman isomorphism test. The new paradigm suggests using subgraphs extracted from the input graph to improve the model's expressiveness, but the additional complexity exacerbates an already challenging problem in GNNs: explaining their predictions. In this work, we adapt PGExplainer, one of the most recent explainers for GNNs, to SGNNs. The proposed explainer accounts for the contribution of all the different subgraphs and can produce a meaningful explanation that humans can interpret. The experiments that we performed both on real and synthetic datasets show that our framework is successful in explaining the decision process of an SGNN on graph classification tasks.