Disentangling Hyperedges through the Lens of Category Theory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Yoonho, Lee, Junseok, Seo, Sangwoo, Kim, Sungwon, Kim, Yeongmin, Park, Chanyoung
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911218411765760
author Lee, Yoonho
Lee, Junseok
Seo, Sangwoo
Kim, Sungwon
Kim, Yeongmin
Park, Chanyoung
author_facet Lee, Yoonho
Lee, Junseok
Seo, Sangwoo
Kim, Sungwon
Kim, Yeongmin
Park, Chanyoung
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2510_16289
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Disentangling Hyperedges through the Lens of Category Theory
Lee, Yoonho
Lee, Junseok
Seo, Sangwoo
Kim, Sungwon
Kim, Yeongmin
Park, Chanyoung
Machine Learning
Artificial Intelligence
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).
title Disentangling Hyperedges through the Lens of Category Theory
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.16289