DWCL: Dual-Weighted Contrastive Learning for Multi-View Clustering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912200591933440 |
|---|---|
| author | Yuan, Hanning Zhang, Zhihui Guo, Qi Chi, Lianhua Ruan, Sijie Pang, Jinhui Hao, Xiaoshuai |
| author_facet | Yuan, Hanning Zhang, Zhihui Guo, Qi Chi, Lianhua Ruan, Sijie Pang, Jinhui Hao, Xiaoshuai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17354 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DWCL: Dual-Weighted Contrastive Learning for Multi-View Clustering Yuan, Hanning Zhang, Zhihui Guo, Qi Chi, Lianhua Ruan, Sijie Pang, Jinhui Hao, Xiaoshuai Computer Vision and Pattern Recognition Machine Learning 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. |
| title | DWCL: Dual-Weighted Contrastive Learning for Multi-View Clustering |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2411.17354 |