mlsanityData to 7 Oct 2026

Disentangling Hyperedges through the Lens of Category Theory

arXiv 2510.16289 ↗First posted 18 Oct 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite the promising results of disentangled representation learning in discovering latent patterns in graph-structured data, few studies have explored disentanglement for hypergraph-structured data. Integrating hyperedge disentanglement into hypergraph neural networks enables models to leverage hidden hyperedge semantics, such as unannotated relations between nodes, that are associated with labels. This paper presents an analysis of hyperedge disentanglement from a category-theoretical perspective and proposes a novel criterion for disentanglement derived from the naturality condition. Our proof-of-concept model experimentally showed the potential of the proposed criterion by successfully capturing functional relations of genes (nodes) in genetic pathways (hyperedges).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 87 references that are in the map. First posted on arXiv 18 Oct 2025.

Builds on

39 of 87 references.

References · 39

  1. 2017Deep Setscited by 1,394
  2. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  3. 2018Hypergraph Neural Networkscited by 482
  4. 2018Towards a Definition of Disentangled Representationscited by 294
  5. 2019Hypergraph Convolution and Hypergraph Attentioncited by 226
  6. 2019What Can Neural Networks Reason About?cited by 155
  7. 2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 127
  8. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  9. 2020HNHN: Hypergraph Networks with Hyperedge Neuronscited by 104
  10. 2021Neural Algorithmic Reasoningcited by 92
  11. 2020Sheaf Neural Networkscited by 80
  12. 2020Factorizable Graph Convolutional Networkscited by 79
27 more
  1. 2020Be More with Less: Hypergraph Attention Networks for Inductive Text Classificationcited by 73
  2. 2022Graph Neural Networks are Dynamic Programmerscited by 55
  3. 2022Equivariant Hypergraph Diffusion Neural Operatorscited by 45
  4. 2017Backprop as Functor: A compositional perspective on supervised learningcited by 44
  5. 2021Categorical Foundations of Gradient-Based Learningcited by 44
  6. 2019Independence Promoted Graph Disentangled Networkscited by 38
  7. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  8. 2022On the Power of Foundation Modelscited by 37
  9. 2021Category Theory in Machine Learningcited by 36
  10. 2020Natural Graph Networkscited by 35
  11. 2023Sheaf Hypergraph Networkscited by 33
  12. 2022Exploring Edge Disentanglement for Node Classificationcited by 23
  13. 2023From Hypergraph Energy Functions to Hypergraph Neural Networkscited by 17
  14. 2023Asynchronous Algorithmic Alignment with Cocyclescited by 13
  15. 2019Lenses and Learnerscited by 11
  16. 2019Compositional Deep Learningcited by 7
  17. 2022SHINE: SubHypergraph Inductive Neural nEtworkcited by 7
  18. 2021Categorical Representation Learning: Morphism is All You Needcited by 6
  19. 2021Sheaves as a Framework for Understanding and Interpreting Model Fitcited by 5
  20. 2022DisenHCN: Disentangled Hypergraph Convolutional Networks for Spatiotemporal Activity Predictioncited by 5
  21. 2019Compositionality for Recursive Neural Networkscited by 4
  22. 2021A Bounded-Confidence Model of Opinion Dynamics on Hypergraphscited by 4
  23. 2023A Categorical Framework of General Intelligencecited by 4
  24. 2023A Category-theoretical Meta-analysis of Definitions of Disentanglementcited by 3
  25. 2022Neural network layers as parametric spanscited by 2
  26. 2019Sheaves: A Topological Approach to Big Datacited by 1
  27. 2024DLGNet: Hyperedge Classification through Directed Line Graphs for Chemical Reactionscited by 1

Built on by

Not cited yet.