Adaptive-weighted deep multi-view clustering with uniform scale representation

doi:10.1016/j.neunet.2023.11.066

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Adaptive-weighted deep multi-view clustering with uniform scale representation
	Chen, Rui 1,2; Tang, Yongqiang 2; Zhang, Wensheng 1,2; Feng, Wenlong 1,3
刊名	NEURAL NETWORKS
	2024-03-01
卷号	171 页码:114-126
关键词	Multi-view clustering Deep clustering Adaptive-weighted learning Uniform scale representation
ISSN号	0893-6080
DOI	10.1016/j.neunet.2023.11.066
通讯作者	Tang, Yongqiang(yongqiang.tang@ia.ac.cn) ; Zhang, Wensheng(zhangwenshengia@hotmail.com)
英文摘要	Multi-view clustering has attracted growing attention owing to its powerful capacity of multi-source information integration. Although numerous advanced methods have been proposed in past decades, most of them generally fail to distinguish the unequal importance of multiple views to the clustering task and overlook the scale uniformity of learned latent representation among different views, resulting in blurry physical meaning and suboptimal model performance. To address these issues, in this paper, we propose a joint learning framework, termed Adaptive-weighted deep Multi-view Clustering with Uniform scale representation (AMCU). Specifically, to achieve more reasonable multi-view fusion, we introduce an adaptive weighting strategy, which imposes simplex constraints on heterogeneous views for measuring their varying degrees of contribution to consensus prediction. Such a simple yet effective strategy shows its clear physical meaning for the multi view clustering task. Furthermore, a novel regularizer is incorporated to learn multiple latent representations sharing approximately the same scale, so that the objective for calculating clustering loss cannot be sensitive to the views and thus the entire model training process can be guaranteed to be more stable as well. Through comprehensive experiments on eight popular real-world datasets, we demonstrate that our proposal performs better than several state-of-the-art single-view and multi-view competitors.
资助项目	National Key Research and Develop-ment Program of China[2020AAA0109500] ; National Natural Science Foundation of China[62106266] ; National Natural Science Foundation of China[U22B2048]
WOS关键词	NONNEGATIVE MATRIX FACTORIZATION
WOS研究方向	Computer Science ; Neurosciences & Neurology
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:001139926700001
资助机构	National Key Research and Develop-ment Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54795]
专题	多模态人工智能系统全国重点实验室
通讯作者	Tang, Yongqiang; Zhang, Wensheng
作者单位	1.Hainan Univ, Coll Informat Sci & Technol, Haikou 570208, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 3.Hainan Univ, State Key Lab Marine Resource Utilizat South China, Haikou 570208, Peoples R China
推荐引用方式 GB/T 7714	Chen, Rui,Tang, Yongqiang,Zhang, Wensheng,et al. Adaptive-weighted deep multi-view clustering with uniform scale representation[J]. NEURAL NETWORKS,2024,171:114-126.
APA	Chen, Rui,Tang, Yongqiang,Zhang, Wensheng,&Feng, Wenlong.(2024).Adaptive-weighted deep multi-view clustering with uniform scale representation.NEURAL NETWORKS,171,114-126.
MLA	Chen, Rui,et al."Adaptive-weighted deep multi-view clustering with uniform scale representation".NEURAL NETWORKS 171(2024):114-126.