Multi-view graph-regularized deep metric subspace clustering network
Pengpeng Luo, Ming Yang, Chong Peng, Qianqian Wang · 2026
Read Multi-view graph-regularized deep metric subspace clustering network by Pengpeng Luo, Ming Yang, Chong Peng, Qianqian Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354307.txt.
Description
Pengpeng Luo and colleagues present a clustering network in a 2026 PLOS ONE paper on grouping multi-view data. Multi-view data describe the same items through several sensors or formats. Clustering sorts unlabeled items into groups, and deep networks now handle tangled, nonlinear patterns, but older methods miss complex shape structure and get little guidance from emerging groups.
The proposed network adds two parts to an efficient earlier design. A graph module keeps both near and next-near shape links between items. A weighted clustering module steers learning toward clear groups while balancing each view's say. On five benchmark datasets, the method beat leading rivals in accuracy and robustness, the authors report.
Catalog record
| CREATOR | Pengpeng Luo, Ming Yang, Chong Peng, Qianqian Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46532 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |