Local and Global Discriminative Learning for Unsupervised Feature Selection

ISCAS OpenIR

	Local and Global Discriminative Learning for Unsupervised Feature Selection
	Du, Liang; Shen, Zhiyong; Li, Xuan; Zhou, Peng; Shen, Yi-Dong
	2013
会议名称	IEEE 13th International Conference on Data Mining (ICDM)
页码	131-140
会议日期	DEC 07-10, 2013
会议地点	Dallas, TX
收录类别	CPCI
出版地	IEEE
ISSN	1550-4786
部门归属	[Du, Liang; Zhou, Peng; Shen, Yi-Dong] Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China.
摘要	In this paper, we consider the problem of feature selection in unsupervised learning scenario. Recently, spectral feature selection methods, which leverage both the graph Laplacian and the learning mechanism, have received considerable attention. However, when there are lots of irrelevant or noisy features, such graphs may not be reliable and then mislead the selection of features. In this paper, we propose the Local and Global Discriminative learning for unsupervised Feature Selection (LGDFS), which integrates a global and a set of locally linear regression model with weighted l(2)-norm regularization into a unified learning framework. By exploring the discriminative and geometrical information in the weighted feature space, which alleviates the effects of the irrelevant features, our approach can find the most representative features to well respect the cluster structure of the data. Experimental results on several benchmark data sets are provided to validate the effectiveness of the proposed approach.; In this paper, we consider the problem of feature selection in unsupervised learning scenario. Recently, spectral feature selection methods, which leverage both the graph Laplacian and the learning mechanism, have received considerable attention. However, when there are lots of irrelevant or noisy features, such graphs may not be reliable and then mislead the selection of features. In this paper, we propose the Local and Global Discriminative learning for unsupervised Feature Selection (LGDFS), which integrates a global and a set of locally linear regression model with weighted l(2)-norm regularization into a unified learning framework. By exploring the discriminative and geometrical information in the weighted feature space, which alleviates the effects of the irrelevant features, our approach can find the most representative features to well respect the cluster structure of the data. Experimental results on several benchmark data sets are provided to validate the effectiveness of the proposed approach.
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16539
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Du, Liang,Shen, Zhiyong,Li, Xuan,et al. Local and Global Discriminative Learning for Unsupervised Feature Selection[C]. IEEE,2013:131-140.