Self-weighted Robust LDA for Multiclass Classification with Edge Classes

Yan, C; Chang, X; Luo, M; Zheng, Q; Zhang, X; Li, Z; Nie, F

Self-weighted Robust LDA for Multiclass Classification with Edge Classes

Yan, C Chang, X

Luo, M Zheng, Q Zhang, X Li, Z Nie, F

Permalink

Publisher:: Association for Computing Machinery (ACM)
Publication Type:: Journal Article
Citation:: ACM Transactions on Intelligent Systems and Technology, 2021, 12, (1), pp. 1-19
Issue Date:: 2021-02-01

Closed Access

	Filename	Description	Size
	3418284 (1).pdf	Published version	1.57 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yan, C
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	Luo, M
dc.contributor.author	Zheng, Q
dc.contributor.author	Zhang, X
dc.contributor.author	Li, Z
dc.contributor.author	Nie, F
dc.date.accessioned	2022-05-26T01:45:50Z
dc.date.available	2022-05-26T01:45:50Z
dc.date.issued	2021-02-01
dc.identifier.citation	ACM Transactions on Intelligent Systems and Technology, 2021, 12, (1), pp. 1-19
dc.identifier.issn	2157-6904
dc.identifier.issn	2157-6912
dc.identifier.uri	http://hdl.handle.net/10453/157711
dc.description.abstract	<jats:p> Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative features for multi-class classification. A vast majority of existing LDA algorithms are prone to be dominated by the class with very large deviation from the others, i.e., edge class, which occurs frequently in multi-class classification. First, the existence of edge classes often makes the total mean biased in the calculation of between-class scatter matrix. Second, the exploitation of ℓ <jats:sub>2</jats:sub> -norm based between-class distance criterion magnifies the extremely large distance corresponding to edge class. In this regard, a novel self-weighted robust LDA with ℓ <jats:sub>2,1</jats:sub> -norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes. SWRLDA can automatically avoid the optimal mean calculation and simultaneously learn adaptive weights for each class pair without setting any additional parameter. An efficient re-weighted algorithm is exploited to derive the global optimum of the challenging ℓ <jats:sub>2,1</jats:sub> -norm maximization problem. The proposed SWRLDA is easy to implement and converges fast in practice. Extensive experiments demonstrate that SWRLDA performs favorably against other compared methods on both synthetic and real-world datasets while presenting superior computational efficiency in comparison with other techniques. </jats:p>
dc.language	English
dc.publisher	Association for Computing Machinery (ACM)
dc.relation.ispartof	ACM Transactions on Intelligent Systems and Technology
dc.relation.isbasedon	10.1145/3418284
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0806 Information Systems
dc.title	Self-weighted Robust LDA for Multiclass Classification with Edge Classes
dc.type	Journal Article
utslib.citation.volume	12
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-05-26T01:45:37Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	12
utslib.citation.issue	1

Abstract:

Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative features for multi-class classification. A vast majority of existing LDA algorithms are prone to be dominated by the class with very large deviation from the others, i.e., edge class, which occurs frequently in multi-class classification. First, the existence of edge classes often makes the total mean biased in the calculation of between-class scatter matrix. Second, the exploitation of ℓ 2 -norm based between-class distance criterion magnifies the extremely large distance corresponding to edge class. In this regard, a novel self-weighted robust LDA with ℓ 2,1 -norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes. SWRLDA can automatically avoid the optimal mean calculation and simultaneously learn adaptive weights for each class pair without setting any additional parameter. An efficient re-weighted algorithm is exploited to derive the global optimum of the challenging ℓ 2,1 -norm maximization problem. The proposed SWRLDA is easy to implement and converges fast in practice. Extensive experiments demonstrate that SWRLDA performs favorably against other compared methods on both synthetic and real-world datasets while presenting superior computational efficiency in comparison with other techniques.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/157711