Bhygnn+: unsupervised representation learning for heterophilic hypergraphs
Open Access
- 26 September 2026
- journal article
- research article
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 68 (1) , 265
Abstract
Hypergraph neural networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on heterophilic hypergraphs, where nodes connected by the same hyperedge tend to have dissimilar semantic representations or belong to different classes. While several HyGNNs, including our prior work BHyGNN, have been proposed to address heterophily, their reliance on labeled data significantly limits their applicability in real-world scenarios where annotations are scarce or costly. To overcome this limitation, we introduce BHyGNN+ , a self-supervised learning framework that extends BHyGNN for representation learning on heterophilic hypergraphs without requiring ground-truth labels. The core idea of BHyGNN+ is hypergraph duality , a structural transformation where the roles of nodes and hyperedges are interchanged. By contrasting augmented views of a hypergraph against its dual using cosine similarity, our framework captures essential structural patterns in a fully unsupervised manner. Notably, this duality-based formulation eliminates the need for negative samples, a common requirement in existing hypergraph contrastive learning methods that is often difficult to satisfy in practice. Extensive experiments on eleven benchmark datasets demonstrate that BHyGNN+ consistently outperforms state-of-the-art supervised and self-supervised baselines on both heterophilic and homophilic hypergraphs. Our results validate the effectiveness of leveraging hypergraph duality for self-supervised learning and establish a new paradigm for representation learning on challenging, unlabeled hypergraphs.Keywords
All Related Versions
Funding Information
- National Science Foundation
This publication has 36 references indexed in Scilit:
- Hypergraph Representation Learning with Adaptive Broadcasting and Receiving2025
- Hypergraph Contrastive Learning for Drug Trafficking Community Detection2023
- Multi-view Self-supervised Heterogeneous Graph Embedding2021
- Hypergraph convolution and hypergraph attentionPattern Recognition, 2021
- Message Passing Neural Networks2020
- Simplicial closure and higher-order link predictionProceedings of the National Academy of Sciences, 2018
- Applications of Hypergraph Theory: A Brief Overview2013
- Legislative cosponsorship networks in the US House and SenateSocial Networks, 2006
- Connecting the Congress: A Study of Cosponsorship NetworksPolitical Analysis, 2006
- Convex Optimization2004