Counterfactual Explanations for Hypergraph Neural Networks
This addresses the interpretability issue for HGNNs, which is crucial for deployment in high-stakes settings, representing an incremental improvement in explanation methods for graph-based models.
The paper tackled the problem of interpreting hypergraph neural networks (HGNNs) by introducing CF-HyperGNNExplainer, a counterfactual explanation method that identifies minimal structural changes to alter predictions, and experiments on three benchmark datasets showed it generates valid and concise counterfactuals.
Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, limiting their deployment in high-stakes settings. We introduce CF-HyperGNNExplainer, a counterfactual explanation method for HGNNs that identifies the minimal structural changes required to alter a model's prediction. The method generates counterfactual hypergraphs using actionable edits limited to removing node-hyperedge incidences or deleting hyperedges, producing concise and structurally meaningful explanations. Experiments on three benchmark datasets show that CF-HyperGNNExplainer generates valid and concise counterfactuals, highlighting the higher-order relations most critical to HGNN decisions.