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

TL;DR

This paper introduces CAHC, an end-to-end contrastive learning method for attributed hypergraph clustering that jointly learns node embeddings and clustering results, outperforming existing methods on multiple datasets.

Contribution

The paper proposes a novel end-to-end contrastive learning framework that integrates representation learning and clustering for attributed hypergraphs, improving clustering accuracy.

Findings

CAHC outperforms baseline methods on eight datasets.

The method effectively combines node and hyperedge objectives.

Joint optimization enhances clustering quality.

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.