GOAt: Explaining Graph Neural Networks via Graph Output Attribution

Shengyao Lu, Keith G Mills, Jiao He, Bang Liu, Di Niu

Keywords: Graph Neural Networks, explainability, interpretability, local-level explanation, instance-level explanation

Abstract: Understanding the decision-making process of Graph Neural Networks (GNNs) is crucial to their interpretability. Present methods for explaining GNNs typically rely on training auxiliary models, and may struggle with issues such as overfitting to noise, insufficient discriminability, and inconsistent explanations across data samples of the same class. This paper introduces Graph Output Attribution (GOAt), a novel method to attribute graph outputs to input graph features, creating GNN explanations that are faithful, discriminative, as well as stable across similar samples. By expanding the GNN as a sum of scalar products involving node features, edge features and activation patterns, we propose an efficient analytical method to compute contribution of each node or edge feature to each scalar product and aggregate the contributions from all scalar products in the expansion form to derive the importance of each node and edge. Through extensive experiments on synthetic and real data, we show that our method has consistently outperformed various state-of-the-art GNN explainers in terms of fidelity, discriminability, and stability.

Submission Number: 10555