Self-weighted dual contrastive multi-view clustering network

Abstract Multi-view Clustering (MVC) has gained significant attention in recent years due to its ability to explore consensus information from multiple perspectives. However, traditional MVC methods face two major challenges: (1) how to alleviate the representation degeneration caused by the process...

Full description

Saved in:
Bibliographic Details
Main Authors: Huajuan Huang, Yanbin Mei, Xiuxi Wei, Yongquan Zhou
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-00895-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849728428748570624
author Huajuan Huang
Yanbin Mei
Xiuxi Wei
Yongquan Zhou
author_facet Huajuan Huang
Yanbin Mei
Xiuxi Wei
Yongquan Zhou
author_sort Huajuan Huang
collection DOAJ
description Abstract Multi-view Clustering (MVC) has gained significant attention in recent years due to its ability to explore consensus information from multiple perspectives. However, traditional MVC methods face two major challenges: (1) how to alleviate the representation degeneration caused by the process of achieving multi-view consensus information, and (2) how to learn discriminative representations with clustering-friendly structures. Most existing MVC methods overlook the importance of inter-cluster separability. To address these issues, we propose a novel Contrastive Learning-based Dual Contrast Mechanism Deep Multi-view Clustering Network. Specifically, we first introduce view-specific autoencoders to extract latent features for each individual view. Then, we obtain consensus information across views through global feature fusion, measuring the pairwise representation discrepancy by maximizing the consistency between the view-specific representations and global feature representations. Subsequently, we design an adaptive weighted mechanism that can automatically enhance the useful views in feature fusion while suppressing unreliable views, effectively mitigating the representation degeneration issue. Furthermore, within the Contrastive Learning framework, we introduce a Dynamic Cluster Diffusion (DC) module that maximizes the distance between different clusters, thus enhancing the separability of the clusters and obtaining a clustering-friendly discriminative representation. Extensive experiments on multiple datasets demonstrate that our method not only achieves state-of-the-art clustering performance but also produces clustering structures with better separability.
format Article
id doaj-art-d45ee0344cff4e7384ec2754115295f0
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d45ee0344cff4e7384ec2754115295f02025-08-20T03:09:34ZengNature PortfolioScientific Reports2045-23222025-05-0115111610.1038/s41598-025-00895-6Self-weighted dual contrastive multi-view clustering networkHuajuan Huang0Yanbin Mei1Xiuxi Wei2Yongquan Zhou3College of Artificial Intelligence, Guangxi Minzu UniversityCollege of Artificial Intelligence, Guangxi Minzu UniversityCollege of Artificial Intelligence, Guangxi Minzu UniversityCollege of Artificial Intelligence, Guangxi Minzu UniversityAbstract Multi-view Clustering (MVC) has gained significant attention in recent years due to its ability to explore consensus information from multiple perspectives. However, traditional MVC methods face two major challenges: (1) how to alleviate the representation degeneration caused by the process of achieving multi-view consensus information, and (2) how to learn discriminative representations with clustering-friendly structures. Most existing MVC methods overlook the importance of inter-cluster separability. To address these issues, we propose a novel Contrastive Learning-based Dual Contrast Mechanism Deep Multi-view Clustering Network. Specifically, we first introduce view-specific autoencoders to extract latent features for each individual view. Then, we obtain consensus information across views through global feature fusion, measuring the pairwise representation discrepancy by maximizing the consistency between the view-specific representations and global feature representations. Subsequently, we design an adaptive weighted mechanism that can automatically enhance the useful views in feature fusion while suppressing unreliable views, effectively mitigating the representation degeneration issue. Furthermore, within the Contrastive Learning framework, we introduce a Dynamic Cluster Diffusion (DC) module that maximizes the distance between different clusters, thus enhancing the separability of the clusters and obtaining a clustering-friendly discriminative representation. Extensive experiments on multiple datasets demonstrate that our method not only achieves state-of-the-art clustering performance but also produces clustering structures with better separability.https://doi.org/10.1038/s41598-025-00895-6Multi-view clusteringDeep clusteringContrastive learningRepresentation degeneration
spellingShingle Huajuan Huang
Yanbin Mei
Xiuxi Wei
Yongquan Zhou
Self-weighted dual contrastive multi-view clustering network
Scientific Reports
Multi-view clustering
Deep clustering
Contrastive learning
Representation degeneration
title Self-weighted dual contrastive multi-view clustering network
title_full Self-weighted dual contrastive multi-view clustering network
title_fullStr Self-weighted dual contrastive multi-view clustering network
title_full_unstemmed Self-weighted dual contrastive multi-view clustering network
title_short Self-weighted dual contrastive multi-view clustering network
title_sort self weighted dual contrastive multi view clustering network
topic Multi-view clustering
Deep clustering
Contrastive learning
Representation degeneration
url https://doi.org/10.1038/s41598-025-00895-6
work_keys_str_mv AT huajuanhuang selfweighteddualcontrastivemultiviewclusteringnetwork
AT yanbinmei selfweighteddualcontrastivemultiviewclusteringnetwork
AT xiuxiwei selfweighteddualcontrastivemultiviewclusteringnetwork
AT yongquanzhou selfweighteddualcontrastivemultiviewclusteringnetwork