Perturb More, Trap More: Understanding Behaviors of Graph Neural Networks
This addresses the problem of interpretability for users of GNNs in graph-based tasks, but it is incremental as it builds on existing explainer methods.
The paper tackles the lack of transparency in graph neural networks (GNNs) by proposing TraP2, a post-hoc explanation framework based on local fidelity, which achieves 10.2% higher explanation accuracy than state-of-the-art methods.
While graph neural networks (GNNs) have shown a great potential in various tasks on graph, the lack of transparency has hindered understanding how GNNs arrived at its predictions. Although few explainers for GNNs are explored, the consideration of local fidelity, indicating how the model behaves around an instance should be predicted, is neglected. In this paper, we first propose a novel post-hoc framework based on local fidelity for any trained GNNs - TraP2, which can generate a high-fidelity explanation. Considering that both relevant graph structure and important features inside each node need to be highlighted, a three-layer architecture in TraP2 is designed: i) interpretation domain are defined by Translation layer in advance; ii) local predictive behavior of GNNs being explained are probed and monitored by Perturbation layer, in which multiple perturbations for graph structure and feature-level are conducted in interpretation domain; iii) high faithful explanations are generated by fitting the local decision boundary through Paraphrase layer. Finally, TraP2 is evaluated on six benchmark datasets based on five desired attributions: accuracy, fidelity, decisiveness, insight and inspiration, which achieves $10.2\%$ higher explanation accuracy than the state-of-the-art methods.