Explainability in subgraphs-enhanced Graph Neural Networks
This work addresses the explainability challenge for researchers and practitioners using SGNNs, but it is incremental as it adapts an existing method rather than introducing a new one.
The paper tackled the problem of explaining predictions in subgraphs-enhanced Graph Neural Networks (SGNNs), which are more complex and harder to interpret than standard GNNs, by adapting the PGExplainer method to account for subgraph contributions, and experiments on real and synthetic datasets showed successful explanations for graph classification tasks.
Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been introduced to enhance the expressive power of Graph Neural Networks (GNNs), which was proved to be not higher than the 1-dimensional Weisfeiler-Leman isomorphism test. The new paradigm suggests using subgraphs extracted from the input graph to improve the model's expressiveness, but the additional complexity exacerbates an already challenging problem in GNNs: explaining their predictions. In this work, we adapt PGExplainer, one of the most recent explainers for GNNs, to SGNNs. The proposed explainer accounts for the contribution of all the different subgraphs and can produce a meaningful explanation that humans can interpret. The experiments that we performed both on real and synthetic datasets show that our framework is successful in explaining the decision process of an SGNN on graph classification tasks.