Global Graph Counterfactual Explanation: A Subgraph Mapping Approach

TL;DR

GlobalGCE introduces a global-level approach to explain GNNs by identifying subgraph mapping rules that broadly influence predictions across many graphs, offering more comprehensive insights than local explanations.

Contribution

The paper presents GlobalGCE, a novel method for global graph counterfactual explanations using subgraph mapping rules, advancing beyond local explanations to provide broader insights.

Findings

GlobalGCE outperforms existing baselines in experiments.

It effectively identifies subgraph rules that influence GNN predictions.

The method achieves high coverage across diverse graph datasets.

Abstract

Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to find minimum perturbations on input graphs that change the GNN predictions. Existing works on GNN counterfactual explanations primarily concentrate on the local-level perspective (i.e., generating counterfactuals for each individual graph), which suffers from information overload and lacks insights into the broader cross-graph relationships. To address such issues, we propose GlobalGCE, a novel global-level graph counterfactual explanation method. GlobalGCE aims to identify a collection of subgraph mapping rules as counterfactual explanations for the target GNN. According to these rules, substituting certain significant subgraphs with their counterfactual subgraphs will change the GNN prediction to the desired class for most graphs (i.e., maximum coverage). Methodologically, we design a significant subgraph generator and a counterfactual subgraph autoencoder in our GlobalGCE, where the subgraphs and the rules can be effectively generated. Extensive experiments demonstrate the superiority of our GlobalGCE compared to existing baselines. Our code can be found at https://anonymous.4open.science/r/GlobalGCE-92E8.