Deep contrastive multi-view clustering with doubly enhanced commonality

Recently, deep multi-view clustering leveraging autoencoders has garnered significant attention due to its ability to simultaneously enhance feature learning capabilities and optimize clustering outcomes. However, existing autoencoder-based deep multi-view clustering methods often exhibit a tendency...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Multimedia systems Ročník 30; číslo 4; s. 196
Hlavní autori: Yang, Zhiyuan, Zhu, Changming, Li, Zishi
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2024
Springer Nature B.V
Predmet:
Clustering
Commonality
Computer Communication Networks
Computer Graphics
Computer Science
Cryptology
Data Storage Representation
Datasets
Dilution
Learning
Multimedia Information Systems
Neural networks
Operating Systems
Regular Paper
Semantics
Training
Autoencoder
Unsupervised learning
Deep multi-view clustering
Contrastive learning
ISSN:0942-4962, 1432-1882
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Recently, deep multi-view clustering leveraging autoencoders has garnered significant attention due to its ability to simultaneously enhance feature learning capabilities and optimize clustering outcomes. However, existing autoencoder-based deep multi-view clustering methods often exhibit a tendency to either overly emphasize view-specific information, thus neglecting shared information across views, or alternatively, to place undue focus on shared information, resulting in the dilution of complementary information from individual views. Given the principle that commonality resides within individuality, this paper proposes a staged training approach that comprises two phases: pre-training and fine-tuning. The pre-training phase primarily focuses on learning view-specific information, while the fine-tuning phase aims to doubly enhance commonality across views while maintaining these specific details. Specifically, we learn and extract the specific information of each view through the autoencoder in the pre-training stage. After entering the fine-tuning stage, we first initially enhance the commonality between independent specific views through the transformer layer, and then further strengthen these commonalities through contrastive learning on the semantic labels of each view, so as to obtain more accurate clustering results.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0942-4962
1432-1882
DOI:10.1007/s00530-024-01400-1