mlsanityData to 7 Oct 2026

Counterfactual Explanations for Hypergraph Neural Networks

arXiv 2602.04360 ↗First posted 4 Feb 2026cs.LG cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 4 Feb 2026.

Builds on

18 of 34 references.

References · 18

  1. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  2. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  3. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  4. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  5. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  6. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  7. 2020Networks beyond pairwise interactions: structure and dynamicscited by 127
  8. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  9. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  10. 2017Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweakingcited by 76
  11. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  12. 2021Generative hypergraph clustering: from blockmodels to modularitycited by 48
6 more
  1. 2019FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensemblescited by 43
  2. 2021ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Modelscited by 25
  3. 2024A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guidecited by 22
  4. 2025Self-Explaining Hypergraph Neural Networks for Diagnosis Predictioncited by 2
  5. 2024Explaining Hypergraph Neural Networks: From Local Explanations to Global Conceptscited by 1
  6. 2025Demystifying Sequential Recommendations: Counterfactual Explanations via Genetic Algorithmscited by 1

Built on by

Not cited yet.