Explainable Graph Neural Networks via Structural Externalities

TL;DR

This paper introduces GraphEXT, a novel explainability framework for GNNs that uses cooperative game theory and social externalities to better capture node interactions and improve model interpretability.

Contribution

GraphEXT is the first method to incorporate social externalities and the Shapley value for explaining GNNs, focusing on node interactions and structural impacts.

Findings

Outperforms baseline methods in fidelity across datasets

Enhances interpretability of various GNN architectures

Effectively captures node interaction effects

Abstract

Graph Neural Networks (GNNs) have achieved outstanding performance across a wide range of graph-related tasks. However, their "black-box" nature poses significant challenges to their explainability, and existing methods often fail to effectively capture the intricate interaction patterns among nodes within the network. In this work, we propose a novel explainability framework, GraphEXT, which leverages cooperative game theory and the concept of social externalities. GraphEXT partitions graph nodes into coalitions, decomposing the original graph into independent subgraphs. By integrating graph structure as an externality and incorporating the Shapley value under externalities, GraphEXT quantifies node importance through their marginal contributions to GNN predictions as the nodes transition between coalitions. Unlike traditional Shapley value-based methods that primarily focus on node attributes, our GraphEXT places greater emphasis on the interactions among nodes and the impact of structural changes on GNN predictions. Experimental studies on both synthetic and real-world datasets show that GraphEXT outperforms existing baseline methods in terms of fidelity across diverse GNN architectures , significantly enhancing the explainability of GNN models.