Summary of Dwcl: Dual-weighted Contrastive Learning For Multi-view Clustering, by Hanning Yuan and Zhihui Zhang and Qi Guo and Lianhua Chi and Sijie Ruan and Jinhui Pang and Xiaoshuai Hao
DWCL: Dual-Weighted Contrastive Learning for Multi-View Clustering
by Hanning Yuan, Zhihui Zhang, Qi Guo, Lianhua Chi, Sijie Ruan, Jinhui Pang, Xiaoshuai Hao
First submitted to arxiv on: 26 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Dual-Weighted Contrastive Learning (DWCL) for Multi-View Clustering addresses challenges in generating consistent clustering structures from multiple views through contrastive learning. The method introduces a Best-Other (B-O) contrastive mechanism to reduce the impact of unreliable cross-views and a dual weighting strategy that combines view quality weight and view discrepancy weight to mitigate representation degeneration. Theoretical analysis validates the efficiency of B-O and effectiveness of dual weighting, while extensive experiments demonstrate DWCL’s superior performance and robustness across eight multi-view datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary DWCL is a new method for clustering data from multiple views. It tries to solve problems in previous methods that combine any two views together, which can be unreliable. DWCL also fixes another problem where the representations of different views become similar, but not perfect. This new method uses a special way of combining views and weighting their importance to get better results. Tests show that DWCL does much better than other methods on many datasets. |
Keywords
» Artificial intelligence » Clustering
