Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Guan, Renchu, Li, Xuyang, Zhang, Yachao, Pang, Wei, Giunchiglia, Fausto, Li, Ximing, Liu, Yonghao, Feng, Xiaoyue
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909920400506880
author Guan, Renchu
Li, Xuyang
Zhang, Yachao
Pang, Wei
Giunchiglia, Fausto
Li, Ximing
Liu, Yonghao
Feng, Xiaoyue
author_facet Guan, Renchu
Li, Xuyang
Zhang, Yachao
Pang, Wei
Giunchiglia, Fausto
Li, Ximing
Liu, Yonghao
Feng, Xiaoyue
contents Hypergraphs, as a generalization of traditional graphs, naturally capture high-order relationships. In recent years, hypergraph neural networks (HNNs) have been widely used to capture complex high-order relationships. However, most existing hypergraph neural network methods inherently rely on the homophily assumption, which often does not hold in real-world scenarios that exhibit significant heterophilic structures. To address this limitation, we propose \textbf{HONOR}, a novel unsupervised \textbf{H}ypergraph c\textbf{ON}trastive learning framework suitable for both hom\textbf{O}philic and hete\textbf{R}ophilic hypergraphs. Specifically, HONOR explicitly models the heterophilic relationships between hyperedges and nodes through two complementary mechanisms: a prompt-based hyperedge feature construction strategy that maintains global semantic consistency while suppressing local noise, and an adaptive attention aggregation module that dynamically captures the diverse local contributions of nodes to hyperedges. Combined with high-pass filtering, these designs enable HONOR to fully exploit heterophilic connection patterns, yielding more discriminative and robust node and hyperedge representations. Theoretically, we demonstrate the superior generalization ability and robustness of HONOR. Empirically, extensive experiments further validate that HONOR consistently outperforms state-of-the-art baselines under both homophilic and heterophilic datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18783
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs
Guan, Renchu
Li, Xuyang
Zhang, Yachao
Pang, Wei
Giunchiglia, Fausto
Li, Ximing
Liu, Yonghao
Feng, Xiaoyue
Machine Learning
Social and Information Networks
Hypergraphs, as a generalization of traditional graphs, naturally capture high-order relationships. In recent years, hypergraph neural networks (HNNs) have been widely used to capture complex high-order relationships. However, most existing hypergraph neural network methods inherently rely on the homophily assumption, which often does not hold in real-world scenarios that exhibit significant heterophilic structures. To address this limitation, we propose \textbf{HONOR}, a novel unsupervised \textbf{H}ypergraph c\textbf{ON}trastive learning framework suitable for both hom\textbf{O}philic and hete\textbf{R}ophilic hypergraphs. Specifically, HONOR explicitly models the heterophilic relationships between hyperedges and nodes through two complementary mechanisms: a prompt-based hyperedge feature construction strategy that maintains global semantic consistency while suppressing local noise, and an adaptive attention aggregation module that dynamically captures the diverse local contributions of nodes to hyperedges. Combined with high-pass filtering, these designs enable HONOR to fully exploit heterophilic connection patterns, yielding more discriminative and robust node and hyperedge representations. Theoretically, we demonstrate the superior generalization ability and robustness of HONOR. Empirically, extensive experiments further validate that HONOR consistently outperforms state-of-the-art baselines under both homophilic and heterophilic datasets.
title Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs
topic Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2511.18783