GraphGI:A GNN Explanation Method using Game Interaction

Graph Neural Networks (GNNs) have garnered significant attention and have been extensively utilized across various domains. However, similar to other deep learning models, GNNs are often viewed as black-box models, making it challenging to interpret their prediction mechanisms. Current graph explanation techniques focus on identifying key nodes or edges, attributing the critical data features that drive model predictions. Nevertheless, these features do not independently influence the model's outcomes; rather, they interact with one another to collectively affect predictions. In this work, we propose a novel explanatory method GraphGI, which identifies the coalition with the highest interaction strength and presents it as an explanatory subgraph. Given a trained model and an input graph, our method explains predictions by gradually incorporating significant edges into the selected subgraph. We utilize game-theoretic interaction values to assess the interaction strength after edge additions, ensuring that the newly added edges confer maximum interaction strength to the explanatory subgraph. To enhance computational efficiency, we adopt effective approximation techniques for calculating Shapley values and game-theoretic interaction values. Empirical evaluations demonstrate that our method achieves superior fidelity and sparsity, maintaining the interpretability of the results at a comprehensible level.