Graph Structure Aware Contrastive Multi-View Clustering

doi:10.1109/TBDATA.2023.3334674

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 人工智能与机器学习

	Graph Structure Aware Contrastive Multi-View Clustering
	Chen, Rui 4,5; Tang, Yongqiang 4; Cai, Xiangrui 3; Yuan, Xiaojie 2; Feng, Wenlong 1,5; Zhang, Wensheng 4,5
刊名	IEEE TRANSACTIONS ON BIG DATA
	2024-06-01
卷号	10 期号:3 页码:260-274
关键词	Correlation Semantics Big Data Representation learning Data models Data mining Analytical models Contrastive learning deep representation graph embedding multi-view clustering
ISSN号	2332-7790
DOI	10.1109/TBDATA.2023.3334674
通讯作者	Tang, Yongqiang(yongqiang.tang@ia.ac.cn)
英文摘要	Multi-view clustering has become a research hotspot in recent decades because of its effectiveness in heterogeneous data fusion. Although a large number of related studies have been developed one after another, most of them usually only concern with the characteristics of the data themselves and overlook the inherent connection among samples, hindering them from exploring structural knowledge of graph space. Moreover, many current works tend to highlight the compactness of one cluster without taking the differences between clusters into account. To track these two drawbacks, in this article, we propose a graph structure aware contrastive multi-view clustering (namely, GCMC) approach. Specifically, we incorporate the well-designed graph autoencoder with conventional multi-layer perception autoencoder to extract the structural and high-level representation of multi-view data, so that the underlying correlation of samples can be effectively squeezed for model learning. Then the contrastive learning paradigm is performed on multiple pseudo-label distributions to ensure that the positive pairs of pseudo-label representations share the complementarity across views while the divergence between negative pairs is sufficiently large. This makes each semantic cluster more discriminative, i.e., jointly satisfying intra-cluster compactness and inter-cluster exclusiveness. Through comprehensive experiments on eight widely-known datasets, we prove that the proposed approach can perform better than the state-of-the-art opponents.
资助项目	National Key Research and Development Program of China
WOS关键词	REPRESENTATION ; ALGORITHM
WOS研究方向	Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001224177900001
资助机构	National Key Research and Development Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58484]
专题	精密感知与控制研究中心_人工智能与机器学习
通讯作者	Tang, Yongqiang
作者单位	1.Hainan Univ, State Key Lab Marine Resource Utilizat South China, Haikou 570228, Peoples R China 2.Nankai Univ, Coll Cyber Sci, Tianjin Key Lab Network & Data Secur Technol, Tianjin 300350, Peoples R China 3.Nankai Univ, Coll Comp Sci, Tianjin 300350, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 5.Hainan Univ, Coll Informat Sci & Technol, Haikou 570228, Peoples R China
推荐引用方式 GB/T 7714	Chen, Rui,Tang, Yongqiang,Cai, Xiangrui,et al. Graph Structure Aware Contrastive Multi-View Clustering[J]. IEEE TRANSACTIONS ON BIG DATA,2024,10(3):260-274.
APA	Chen, Rui,Tang, Yongqiang,Cai, Xiangrui,Yuan, Xiaojie,Feng, Wenlong,&Zhang, Wensheng.(2024).Graph Structure Aware Contrastive Multi-View Clustering.IEEE TRANSACTIONS ON BIG DATA,10(3),260-274.
MLA	Chen, Rui,et al."Graph Structure Aware Contrastive Multi-View Clustering".IEEE TRANSACTIONS ON BIG DATA 10.3(2024):260-274.