Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning

doi:10.1109/TNNLS.2020.2980960

CASIA OpenIR > 离退休人员

	Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning
	Xu, Jiamiao 1; Wang, Fangzhao 1; Peng, Qinmu 1,2; You, Xinge 1,2; Wang, Shuo 1; Jing, Xiao-Yuan 3; Chen, C. L. Philip 4,5,6
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2021-03-01
卷号	32 期号:3 页码:1204-1216
通讯作者	Peng, Qinmu(pqinmu@gmail.com)
摘要	Low-rank Multiview Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL-based methods are incapable of handling well view discrepancy and discriminancy simultaneously, which, thus, leads to performance degradation when there is a large discrepancy among multiview data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose structured low-rank matrix recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of the structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address the data contaminated by the predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical, since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such a limitation, modal regression is elegantly incorporated into the framework of SLMR (termed MR-SLMR). Different from previous LMvSL-based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise, and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to optimize efficiently MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise.
关键词	Robustness Laplace equations Technological innovation Learning systems Data models Gaussian noise Convex functions Block-diagonal representation learning cross-view classification low-rank representation multiview learning
DOI	10.1109/TNNLS.2020.2980960
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[11671161] ; National Natural Science Foundation of China[61571205] ; National Natural Science Foundation of China[61772220] ; Key Program for International S&T Cooperation Projects of China[2016YFE0121200] ; Special Projects for Technology Innovation of Hubei Province[2018ACA135] ; Key Science and Technology Innovation Program of Hubei Province[2017AAA017] ; Natural Science Foundation of Hubei Province[2018CFB691] ; Science, Technology and Innovation Commission of Shenzhen Municipality[JCYJ20180305180637611] ; Science, Technology and Innovation Commission of Shenzhen Municipality[JCYJ20180305180804836] ; Science, Technology and Innovation Commission of Shenzhen Municipality[JSGG20180507182030600]
项目资助者	National Natural Science Foundation of China ; Key Program for International S&T Cooperation Projects of China ; Special Projects for Technology Innovation of Hubei Province ; Key Science and Technology Innovation Program of Hubei Province ; Natural Science Foundation of Hubei Province ; Science, Technology and Innovation Commission of Shenzhen Municipality
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000626332700021
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/44080
专题	离退休人员
通讯作者	Peng, Qinmu
作者单位	1.Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Peoples R China 2.Huazhong Univ Sci & Technol, Shenzhen Res Inst, Shenzhen 518000, Peoples R China 3.Wuhan Univ, Sch Comp, State Key Lab Software Engn, Wuhan 430072, Peoples R China 4.Univ Macau, Fac Sci & Technol, Dept Comp & Informat Sci, Macau 99999, Peoples R China 5.Dalian Maritime Univ, Nav Coll, Dalian 116026, Peoples R China 6.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Xu, Jiamiao,Wang, Fangzhao,Peng, Qinmu,et al. Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021,32(3):1204-1216.
APA	Xu, Jiamiao.,Wang, Fangzhao.,Peng, Qinmu.,You, Xinge.,Wang, Shuo.,...&Chen, C. L. Philip.(2021).Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,32(3),1204-1216.
MLA	Xu, Jiamiao,et al."Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 32.3(2021):1204-1216.