Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs

TL;DR

HONOR is a novel unsupervised hypergraph contrastive learning framework that effectively captures both homophilic and heterophilic relationships, leading to improved node and hyperedge representations in diverse hypergraph structures.

Contribution

The paper introduces HONOR, a new contrastive learning method for hypergraphs that models heterophilic relationships and outperforms existing methods on various datasets.

Findings

HONOR outperforms state-of-the-art baselines on multiple datasets.

Theoretical analysis shows superior generalization and robustness.

Effective modeling of heterophilic relationships enhances representation quality.

Abstract

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.