CVLGNov 26, 2024

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

arXiv:2411.17354v2h-index: 4
Originality Incremental advance
AI Analysis

This addresses multi-view clustering for data analysis, offering incremental improvements in handling view discrepancies and unreliable pairs.

The paper tackles the problem of unreliable cross-view pairs and representation degeneration in multi-view contrastive clustering by introducing DWCL, which uses a Best-Other contrastive mechanism and dual weighting strategy, achieving absolute accuracy improvements of 5.4% and 5.6% on Caltech6V7 and MSRCv1 datasets compared to state-of-the-art methods.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes