Global Counterfactual Explainer for Graph Neural Networks

TL;DR

This paper introduces GCFExplainer, a global counterfactual explanation method for GNNs that identifies representative graphs to explain overall model behavior, improving recourse coverage and reducing explanation complexity.

Contribution

The paper presents GCFExplainer, a novel algorithm for global counterfactual explanations of GNNs using vertex-reinforced random walks and greedy summarization, addressing limitations of local explanations.

Findings

Achieves 46.9% higher recourse coverage.

Reduces recourse cost by 9.5%.

Provides high-level insights into GNN behavior.

Abstract

Graph neural networks (GNNs) find applications in various domains such as computational biology, natural language processing, and computer security. Owing to their popularity, there is an increasing need to explain GNN predictions since GNNs are black-box machine learning models. One way to address this is counterfactual reasoning where the objective is to change the GNN prediction by minimal changes in the input graph. Existing methods for counterfactual explanation of GNNs are limited to instance-specific local reasoning. This approach has two major limitations of not being able to offer global recourse policies and overloading human cognitive ability with too much information. In this work, we study the global explainability of GNNs through global counterfactual reasoning. Specifically, we want to find a small set of representative counterfactual graphs that explains all input graphs. Towards this goal, we propose GCFExplainer, a novel algorithm powered by vertex-reinforced random walks on an edit map of graphs with a greedy summary. Extensive experiments on real graph datasets show that the global explanation from GCFExplainer provides important high-level insights of the model behavior and achieves a 46.9% gain in recourse coverage and a 9.5% reduction in recourse cost compared to the state-of-the-art local counterfactual explainers.