From Representation to Clusters: A Contrastive Learning Approach for Attributed Hypergraph Clustering

2026-03-10

AI Summary

This work addresses the limitation of existing contrastive learning–based attribute hypergraph clustering methods, which lack explicit clustering supervision and thus may encode irrelevant information into node representations. To overcome this, we propose CAHC, a novel approach that, for the first time, directly incorporates clustering supervision signals into the contrastive learning process. CAHC employs an end-to-end framework to jointly optimize node representations and cluster assignments by integrating dual-granularity contrastive learning at both the node and hyperedge levels, along with a differentiable clustering assignment mechanism. This design enables synergistic optimization between representation learning and clustering. Extensive experiments on eight real-world datasets demonstrate that CAHC significantly outperforms current state-of-the-art baselines, confirming its effectiveness and robustness.

Technology Category

• Machine Learning: Clustering
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

Contrastive learning has demonstrated strong performance in attributed hypergraph clustering. Typically, existing methods based on contrastive learning first learn node embeddings and then apply clustering algorithms, such as k-means, to these embeddings to obtain the clustering results.However, these methods lack direct clustering supervision, risking the inclusion of clustering-irrelevant information in the learned graph.To this end, we propose a Contrastive learning approach for Attributed Hypergraph Clustering (CAHC), an end-to-end method that simultaneously learns node embeddings and obtains clustering results. CAHC consists of two main steps: representation learning and cluster assignment learning. The former employs a novel contrastive learning approach that incorporates both node-level and hyperedge-level objectives to generate node embeddings.The latter joint embedding and clustering optimization to refine these embeddings by clustering-oriented guidance and obtains clustering results simultaneously.Extensive experimental results demonstrate that CAHC outperforms baselines on eight datasets.

Problem

• attributed hypergraph clustering
• contrastive learning
• clustering supervision
• node embeddings
• hypergraph representation

Innovation

• contrastive learning
• attributed hypergraph clustering
• end-to-end clustering
• node embedding
• cluster-oriented optimization