A generalized least-squares approach regularized with graph embedding for dimensionality reduction

doi:10.1016/j.patcog.2019.107023

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	A generalized least-squares approach regularized with graph embedding for dimensionality reduction
	Shen, Xiang-Jun 4; Liu, Si-Xing 4; Bao, Bing-Kun 1; Pan, Chun-Hong 5; Zha, Zheng-Jun 3; Fan, Jianping 2
刊名	PATTERN RECOGNITION
	2020-02-01
卷号	98 页码:10
关键词	Dimensionality reduction Graph embedding Subspace learning Least-squares
ISSN号	0031-3203
DOI	10.1016/j.patcog.2019.107023
通讯作者	Shen, Xiang-Jun(xjshen@ujs.edu.cn) ; Zha, Zheng-Jun(zhazj@ustc.edu.cn)
英文摘要	In current graph embedding methods, low dimensional projections are obtained by preserving either global geometrical structure of data or local geometrical structure of data. In this paper, the PCA (Principal Component Analysis) idea of minimizing least-squares reconstruction errors is regularized with graph embedding, to unify various local manifold embedding methods within a generalized framework to keep global and local low dimensional subspace. Different from the well-known PCA method, our proposed generalized least-squares approach considers data distributions together with an instance penalty in each data point. In this way, PCA is viewed as a special instance of our proposed generalized least squares framework for preserving global projections. Applying a regulation of graph embedding, we can obtain projection that preserves both intrinsic geometrical structure and global structure of data. From the experimental results on a variety of face and handwritten digit recognition, our proposed method has advantage of superior performances in keeping lower dimensional subspaces and higher classification results than state-of-the-art graph embedding methods. (C) 2019 Elsevier Ltd. All rights reserved.
资助项目	National Natural Science Foundation of China[61572240] ; National Natural Science Foundation of China[61622211] ; National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[61572503] ; National Natural Science Foundation of China[61872424] ; National Natural Science Foundation of China[6193000388] ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR)[201600005]
WOS关键词	PRESERVING PROJECTIONS ; EIGENMAPS ; FRAMEWORK
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000497600300024
资助机构	National Natural Science Foundation of China ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/29385]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Shen, Xiang-Jun; Zha, Zheng-Jun
作者单位	1.Nanjing Univ Posts & Telecommun, Nanjing, Jiangsu, Peoples R China 2.Univ N Carolina, Dept Comp Sci, Charlotte, NC 28223 USA 3.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei, Anhui, Peoples R China 4.JiangSu Univ, Sch Comp Sci & Commun Engn, Nanjing 212013, Jiangsu, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Shen, Xiang-Jun,Liu, Si-Xing,Bao, Bing-Kun,et al. A generalized least-squares approach regularized with graph embedding for dimensionality reduction[J]. PATTERN RECOGNITION,2020,98:10.
APA	Shen, Xiang-Jun,Liu, Si-Xing,Bao, Bing-Kun,Pan, Chun-Hong,Zha, Zheng-Jun,&Fan, Jianping.(2020).A generalized least-squares approach regularized with graph embedding for dimensionality reduction.PATTERN RECOGNITION,98,10.
MLA	Shen, Xiang-Jun,et al."A generalized least-squares approach regularized with graph embedding for dimensionality reduction".PATTERN RECOGNITION 98(2020):10.