Preserving bilateral view structural information for subspace clustering

Chong Peng; Jing Zhang; Yongyong Chen; Xin Xing; Chenglizhao Chen; Zhao Kang; Li Guo; Qiang Cheng

doi:10.1016/j.knosys.2022.109915

Preserving bilateral view structural information for subspace clustering

Chong Peng
, Jing Zhang
, Yongyong Chen
, Xin Xing
, Chenglizhao Chen
, Zhao Kang
, Li Guo
, Qiang Cheng

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

Abstract

Subspace clustering algorithms have been found successful in various applications that involve two-dimensional data, i.e., each example of the data is a matrix. However, most of the existing methods transform the matrix-type examples to vectors in a pre-processing step, which omits and severely damages the inherent structural information of such data. In this paper, we propose a novel subspace clustering method for two-dimensional data, which is capable of extracting the most representative structural information from the data to recover the underlying grouping relationships of the data. The structural features are extracted from two views of the data and the numbers of feature spaces in both views are automatically determined by optimization. Extensive experiments confirm the effectiveness of the proposed method.

Original language	English
Article number	109915
Journal	Knowledge-Based Systems
Volume	258
DOIs	https://doi.org/10.1016/j.knosys.2022.109915
State	Published - Dec 22 2022

Bibliographical note

Publisher Copyright:
© 2022 Elsevier B.V.

Funding

This work was supported by in part by the National Natural Science Foundation of China (NSFC) under Grants 62172246 , 62106063 , 61802215 , and 61806045 ; in part by the Natural Science Foundation of Shandong Province under Grants ZR2019QF009 and ZR2019BF011 ; in part by the Guangdong Natural Science Foundation under Grant 2022A1515010819 ; in part by the Shenzhen College Stability Support Plan under Grant GXWD20201230155427003-20200824113231001 ; in part by the Shandong Province Colleges and Universities Youth Innovation Technology Plan Innovation Team Project under Grant 2021KJ062 and Grant 2020KJN011 ; in part by the Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies under Grant 2022B1212010005 ; and in part by the National Institutes of Health (NIH) under Grants R21AG070909 and UH3 NS100606-03 .

Funders	Funder number
Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies	2022B1212010005
Shandong Province Colleges and Universities Youth Innovation Technology Plan Innovation Team Project, China	2020KJN011, 2021KJ062
Shenzhen College Stability Support Plan, China	GXWD20201230155427003-20200824113231001
National Institutes of Health (NIH)	UH3 NS100606-03, R21AG070909
National Institutes of Health (NIH)
National Natural Science Foundation of China (NSFC)	62106063, 61806045, 62172246, 61802215
National Natural Science Foundation of China (NSFC)
Natural Science Foundation of Guangdong Province	2022A1515010819
Natural Science Foundation of Guangdong Province
Natural Science Foundation of Shandong Province	ZR2019BF011, ZR2019QF009
Natural Science Foundation of Shandong Province

Keywords

Ridge regression
Structural information
Subspace clustering
Two-dimensional data

ASJC Scopus subject areas

Management Information Systems
Software
Information Systems and Management
Artificial Intelligence

Access to Document

10.1016/j.knosys.2022.109915

Cite this

@article{eb36537377ae467ca7a299a8d98126e7,

title = "Preserving bilateral view structural information for subspace clustering",

abstract = "Subspace clustering algorithms have been found successful in various applications that involve two-dimensional data, i.e., each example of the data is a matrix. However, most of the existing methods transform the matrix-type examples to vectors in a pre-processing step, which omits and severely damages the inherent structural information of such data. In this paper, we propose a novel subspace clustering method for two-dimensional data, which is capable of extracting the most representative structural information from the data to recover the underlying grouping relationships of the data. The structural features are extracted from two views of the data and the numbers of feature spaces in both views are automatically determined by optimization. Extensive experiments confirm the effectiveness of the proposed method.",

keywords = "Ridge regression, Structural information, Subspace clustering, Two-dimensional data",

author = "Chong Peng and Jing Zhang and Yongyong Chen and Xin Xing and Chenglizhao Chen and Zhao Kang and Li Guo and Qiang Cheng",

note = "Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = dec,

day = "22",

doi = "10.1016/j.knosys.2022.109915",

language = "English",

volume = "258",

journal = "Knowledge-Based Systems",

issn = "0950-7051",

publisher = "Elsevier BV",

}

TY - JOUR

T1 - Preserving bilateral view structural information for subspace clustering

AU - Peng, Chong

AU - Zhang, Jing

AU - Chen, Yongyong

AU - Xing, Xin

AU - Chen, Chenglizhao

AU - Kang, Zhao

AU - Guo, Li

AU - Cheng, Qiang

PY - 2022/12/22

Y1 - 2022/12/22

N2 - Subspace clustering algorithms have been found successful in various applications that involve two-dimensional data, i.e., each example of the data is a matrix. However, most of the existing methods transform the matrix-type examples to vectors in a pre-processing step, which omits and severely damages the inherent structural information of such data. In this paper, we propose a novel subspace clustering method for two-dimensional data, which is capable of extracting the most representative structural information from the data to recover the underlying grouping relationships of the data. The structural features are extracted from two views of the data and the numbers of feature spaces in both views are automatically determined by optimization. Extensive experiments confirm the effectiveness of the proposed method.

AB - Subspace clustering algorithms have been found successful in various applications that involve two-dimensional data, i.e., each example of the data is a matrix. However, most of the existing methods transform the matrix-type examples to vectors in a pre-processing step, which omits and severely damages the inherent structural information of such data. In this paper, we propose a novel subspace clustering method for two-dimensional data, which is capable of extracting the most representative structural information from the data to recover the underlying grouping relationships of the data. The structural features are extracted from two views of the data and the numbers of feature spaces in both views are automatically determined by optimization. Extensive experiments confirm the effectiveness of the proposed method.

KW - Ridge regression

KW - Structural information

KW - Subspace clustering

KW - Two-dimensional data

UR - https://www.scopus.com/pages/publications/85140139122

UR - https://www.scopus.com/pages/publications/85140139122#tab=citedBy

U2 - 10.1016/j.knosys.2022.109915

DO - 10.1016/j.knosys.2022.109915

M3 - Article

AN - SCOPUS:85140139122

SN - 0950-7051

VL - 258

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

M1 - 109915

ER -

Preserving bilateral view structural information for subspace clustering

Abstract

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this