Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability
This addresses the need for more interpretable graph classification models, though it is incremental as it builds on existing subgraph-enhanced frameworks.
The paper tackles the problem of improving both expressivity and interpretability in graph neural networks by selecting meaningful subgraphs, achieving comparable accuracy to standard methods while providing explanatory subgraphs.
Subgraph-enhanced graph neural networks (SGNN) can increase the expressive power of the standard message-passing framework. This model family represents each graph as a collection of subgraphs, generally extracted by random sampling or with hand-crafted heuristics. Our key observation is that by selecting "meaningful" subgraphs, besides improving the expressivity of a GNN, it is also possible to obtain interpretable results. For this purpose, we introduce a novel framework that jointly predicts the class of the graph and a set of explanatory sparse subgraphs, which can be analyzed to understand the decision process of the classifier. We compare the performance of our framework against standard subgraph extraction policies, like random node/edge deletion strategies. The subgraphs produced by our framework allow to achieve comparable performance in terms of accuracy, with the additional benefit of providing explanations.