.png){kind=icon}
Return
Balanced Multi-View Clustering
.png){kind=icon}
PRE
AI
DOI：10.1109/tpami.2026.3688728.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC potentially does not fully leverage the multi-view information, due to the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, an analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches both on eight benchmark MvC datasets and two spatially resolved transcriptomics datasets.
Keywords:
Balanced learning
contrastive learning
multi-view clustering
multi-view learning
view cooperation
Journal
IF:
18.6
Papers:
1.1K
Citations:
9.8W
Organization
Cited Papers
Graph Regularized and Feature Aware Matrix Factorization for Robust Incomplete Multi-View Clustering
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSaveSingle-cell RNA and protein profiling of immune cells from the mouse brain and its border tissues.png)
NATURE PROTOCOLS
NATURE PROTOCOLSIF16
PREAI
ShareSave
View more