Communication Dans Un Congrès Année : 2025

HYGENE: A Diffusion-Based Hypergraph Generation Method

Résumé

Hypergraphs are powerful mathematical structures that can model complex, high-order relationships in various domains, including social networks, bioinformatics, and recommender systems. However, generating realistic and diverse hypergraphs remains challenging due to their inherent complexity and lack of effective generative models. In this paper, we introduce a diffusion-based Hypergraph Generation (HYGENE) method that addresses these challenges through a progressive local expansion approach. HYGENE works on the bipartite representation of hypergraphs, starting with a single pair of connected nodes and iteratively expanding it to form the target hypergraph. At each step, nodes and hyperedges are added in a localized manner using a denoising diffusion process, which allows for the construction of the global structure before refining local details. Our experiments demonstrated the effectiveness of HYGENE, proving its ability to closely mimic a variety of properties in hypergraphs. To the best of our knowledge, this is the first attempt to employ diffusion models for hypergraph generation.

Fichier principal
Vignette du fichier
arxiv_HypergraphGeneration-1.pdf (7.43 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05166733 , version 1 (07-08-2025)

Licence

Identifiants

Citer

Dorian Gailhard, Enzo Tartaglione, Lirida Naviner, Jhony Giraldo. HYGENE: A Diffusion-Based Hypergraph Generation Method. The 39th AAAI Conference on Artificial Intelligence e (AAAI-25), Association for the Advancement of Artificial Intelligence, Feb 2025, Philadelphia, United States. pp.16682-16690, ⟨10.1609/aaai.v39i16.33833⟩. ⟨hal-05166733⟩
1300 Consultations
212 Téléchargements

Altmetric

Partager

  • More