Explaining Graph Neural Networks via Structure-aware Interaction Index

TL;DR

This paper introduces the Myerson-Taylor interaction index for explaining graph neural networks by incorporating graph structure into importance and interaction attribution, leading to more accurate motif explanations.

Contribution

The paper proposes the Myerson-Taylor index and the MAGE explainer, which uniquely incorporate graph structure and high-order interactions for more faithful GNN explanations.

Findings

MAGE outperforms existing explainers in identifying important motifs.

The Myerson-Taylor index satisfies natural axioms for structured input attribution.

Experiments show improved explanation quality across multiple datasets.

Abstract

The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, such as graph neural networks, existing Shapley-based explainability approaches either focus solely on node-wise importance or neglect the graph structure when perturbing the input instance. This paper introduces the Myerson-Taylor interaction index that internalizes the graph structure into attributing the node values and the interaction values among nodes. Unlike the Shapley-based methods, the Myerson-Taylor index decomposes coalitions into components satisfying a pre-chosen connectivity criterion. We prove that the Myerson-Taylor index is the unique one that satisfies a system of five natural axioms accounting for graph structure and high-order interaction among nodes. Leveraging these properties, we propose Myerson-Taylor Structure-Aware Graph Explainer (MAGE), a novel explainer that uses the second-order Myerson-Taylor index to identify the most important motifs influencing the model prediction, both positively and negatively. Extensive experiments on various graph datasets and models demonstrate that our method consistently provides superior subgraph explanations compared to state-of-the-art methods.