ServiceNow Research

Explaining Graph Neural Networks Using Interpretable Local Surrogates


We propose an interpretable local surrogate (ILS) method for understanding the predictions of black-box graph models. Explainability methods are commonly employed to gain insights into black-box models and, given the widespread adoption of GNNs in diverse applications, understanding the underlying reasoning behind their decision-making processes becomes crucial. Our ILS method approximates the behavior of a black-box graph model by fitting a simple surrogate model in the local neighborhood of a given input example. Leveraging the interpretability of the surrogate, ILS is able to identify the most relevant nodes contributing to a specific prediction. To efficiently identify these nodes, we utilize group sparse linear models as local surrogates. Through empirical evaluations on explainability benchmarks, our method consistently outperforms state-of-the-art graph explainability methods. This demonstrates the effectiveness of our approach in providing enhanced interpretability for GNN predictions.

Workshop at the International Conference on Machine Learning (ICML)
Perouz Taslakian
Perouz Taslakian
Research Lead

Research Lead at Low Data Learning located at Montreal, QC, Canada.