A feature selection method for multivariate performance measures

Mao, Q; Tsang, IWH

A feature selection method for multivariate performance measures

Mao, Q Tsang, IWH

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35 (9), pp. 2051 - 2063
Issue Date:: 2013-08-05

Closed Access

	Filename	Description	Size
	2013003391OK.pdf		1.18 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	Mao, Q	en_US
dc.contributor.author	Tsang, IWH https://orcid.org/0000-0001-8095-4637	en_US
dc.date.issued	2013-08-05	en_US
dc.identifier.citation	IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35 (9), pp. 2051 - 2063	en_US
dc.identifier.issn	0162-8828	en_US
dc.identifier.uri	http://hdl.handle.net/10453/28296
dc.description.abstract	Feature selection with specific multivariate performance measures is the key to the success of many applications such as image retrieval and text classification. The existing feature selection methods are usually designed for classification error. In this paper, we propose a generalized sparse regularizer. Based on the proposed regularizer, we present a unified feature selection framework for general loss functions. In particular, we study the novel feature selection paradigm by optimizing multivariate performance measures. The resultant formulation is a challenging problem for high-dimensional data. Hence, a two-layer cutting plane algorithm is proposed to solve this problem, and the convergence is presented. In addition, we adapt the proposed method to optimize multivariate measures for multiple-instance learning problems. The analyses by comparing with the state-of-the-art feature selection methods show that the proposed method is superior to others. Extensive experiments on large-scale and high-dimensional real-world datasets show that the proposed method outperforms ( -1)-SVM and SVM-RFE when choosing a small subset of features, and achieves significantly improved performances over ({\rm SVM}^{perf}) in terms of (F-1)-score. © 1979-2012 IEEE.	en_US
dc.relation.ispartof	IEEE Transactions on Pattern Analysis and Machine Intelligence	en_US
dc.relation.isbasedon	10.1109/TPAMI.2012.266	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	A feature selection method for multivariate performance measures	en_US
dc.type	Journal Article
utslib.citation.volume	9	en_US
utslib.citation.volume	35	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0806 Information Systems	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
pubs.embargo.period	Not known	en_US
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/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.issue	9	en_US
pubs.publication-status	Published	en_US
pubs.volume	35	en_US

Abstract:

Feature selection with specific multivariate performance measures is the key to the success of many applications such as image retrieval and text classification. The existing feature selection methods are usually designed for classification error. In this paper, we propose a generalized sparse regularizer. Based on the proposed regularizer, we present a unified feature selection framework for general loss functions. In particular, we study the novel feature selection paradigm by optimizing multivariate performance measures. The resultant formulation is a challenging problem for high-dimensional data. Hence, a two-layer cutting plane algorithm is proposed to solve this problem, and the convergence is presented. In addition, we adapt the proposed method to optimize multivariate measures for multiple-instance learning problems. The analyses by comparing with the state-of-the-art feature selection methods show that the proposed method is superior to others. Extensive experiments on large-scale and high-dimensional real-world datasets show that the proposed method outperforms ( -1)-SVM and SVM-RFE when choosing a small subset of features, and achieves significantly improved performances over ({\rm SVM}^{perf}) in terms of (F-1)-score. © 1979-2012 IEEE.

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

http://hdl.handle.net/10453/28296