.png){kind=icon}
Return
Variational inference framework for partial multi-view multi-label representation learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113742.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Multi-view random dropping augmentation improves model generalization. • Learns joint representation by optimizing three mutual information terms. • The proposed framework explains the process for learning optimal shared information.
Keywords:
multi-view learning
variational inference
mutual information
representation learning
random dropping augmentation
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSaveAn effective bipartite graph fusion and contrastive label correlation for multi-view multi-label classification.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveMulti-level information fusion for missing multi-label learning based on stochastic concept clusteringINFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
ShareSaveShareSaveShareSave
View more