Counterfactual Explanations for Hypergraph Neural Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914595861430272 |
|---|---|
| author | Veglianti, Fabiano Antonelli, Lorenzo Tolomei, Gabriele |
| author_facet | Veglianti, Fabiano Antonelli, Lorenzo Tolomei, Gabriele |
| contents | 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. Extensive experiments on hypergraph benchmark datasets show that CF-HyperGNNExplainer generates valid and concise counterfactuals, highlighting the higher-order relations most critical to HGNN decisions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04360 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Counterfactual Explanations for Hypergraph Neural Networks Veglianti, Fabiano Antonelli, Lorenzo Tolomei, Gabriele Machine Learning Artificial Intelligence Computers and Society 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. Extensive experiments on hypergraph benchmark datasets show that CF-HyperGNNExplainer generates valid and concise counterfactuals, highlighting the higher-order relations most critical to HGNN decisions. |
| title | Counterfactual Explanations for Hypergraph Neural Networks |
| topic | Machine Learning Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2602.04360 |