.png){kind=icon}
.png){kind=icon}
Return
One-step incomplete multi-view clustering based on joint consistent representation learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.132391.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The incomplete multi-view clustering algorithms learn representation graphs for clustering by effectively imputing missing instances and exploring inter-view relationships. Existing methods, however, fail to sufficiently capture the consistencies and higher-order correlations across views. To address this issue, we propose a one-step incomplete multi-view clustering algorithm, named OCRL, which effectively learns and utilizes the joint consistent structures across views. OCRL simultaneously sparsifies inconsistencies within and between views, while integrating the weighted tensor Schatten- norm to capture higher-order correlations across views. Then, OCRL uses one-step clustering to align the consistent structures of all views, directly yielding clear cluster structures. Experiments on various incomplete datasets demonstrate that OCRL significantly outperforms the state-of-the-art baselines.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available