Explaining Graph Neural Networks Using Interpretable Local Surrogates

Farzaneh Heidari, Perouz Taslakian, Guillaume Rabusseau

Keywords: explainability, graph neural networks, surrogate function, interpretable function

TL;DR: We propose ILS, an instance-based method that interprets black-box graph models by approximating them within the local neighborhood using group sparse surrogates, identifying relevant nodes.

Abstract:

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.

Type Of Submission: Proceedings Track (8 pages)

Submission Number: 41