DWCL: Dual-Weighted Contrastive Learning for Multi-View Clustering

TL;DR

This paper introduces DWCL, a novel multi-view clustering method that uses dual-weighted contrastive learning to improve representation quality and robustness across multiple datasets.

Contribution

The paper proposes a dual-weighted contrastive learning framework with a B-O contrastive mechanism to enhance multi-view clustering performance.

Findings

DWCL outperforms previous methods on eight datasets.

Achieves 5.4% and 5.6% accuracy improvements on Caltech6V7 and MSRCv1.

Theoretical validation of the proposed mechanisms.

Abstract

Multi-view contrastive clustering (MVCC) has gained significant attention for generating consistent clustering structures from multiple views through contrastive learning. However, most existing MVCC methods create cross-views by combining any two views, leading to a high volume of unreliable pairs. Furthermore, these approaches often overlook discrepancies in multi-view representations, resulting in representation degeneration. To address these challenges, we introduce a novel model called Dual-Weighted Contrastive Learning (DWCL) for Multi-View Clustering. Specifically, to reduce the impact of unreliable cross-views, we introduce an innovative Best-Other (B-O) contrastive mechanism that enhances the representation of individual views at a low computational cost. Furthermore, we develop a dual weighting strategy that combines a view quality weight, reflecting the quality of each view, with a view discrepancy weight. This approach effectively mitigates representation degeneration by downplaying cross-views that are both low in quality and high in discrepancy. We theoretically validate the efficiency of the B-O contrastive mechanism and the effectiveness of the dual weighting strategy. Extensive experiments demonstrate that DWCL outperforms previous methods across eight multi-view datasets, showcasing superior performance and robustness in MVCC. Specifically, our method achieves absolute accuracy improvements of 5.4\% and 5.6\% compared to state-of-the-art methods on the Caltech6V7 and MSRCv1 datasets, respectively.