Co-regularized unsupervised feature selection

被引:55
|
作者
Zhu, Pengfei [1 ]
Xu, Qian [1 ]
Hu, Qinghua [1 ]
Zhang, Changqing [1 ]
机构
[1] Tianjin Univ, Sch Comp Sci & Technol, Tianjin, Peoples R China
基金
中国国家自然科学基金;
关键词
Feature selection; Co-regularized learning; Data distribution; Data reconstruction;
D O I
10.1016/j.neucom.2017.11.061
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Unsupervised feature selection (UFS) is very challenging due to the lack of label information. Most UFS methods generate pseudo labels by spectral clustering, matrix factorization or dictionary learning, and convert UFS into a supervised feature selection problem. Generally, the features that can preserve the data distribution (i.e., cluster indicator matrix) should be selected. Under the matrix factorization framework, when the cluster indicator matrix is orthogonal, the cluster base (center) matrix can be used to select features that well reconstruct the data. However, almost all the UFS algorithms only select features that can either well preserve the cluster structure or reconstruct the data. In this paper, we propose a novel co-regularized unsupervised feature selection (CUFS) algorithm. Joint l(2,1)-norm co-regularization is imposed on multiple feature selection matrices to ensure that the selected features can both preserve data distribution and data reconstruction. Extensive experiments on benchmark datasets show that CUFS is superior to the state-of-the-art UFS algorithms. (c) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:2855 / 2863
页数:9
相关论文
共 50 条
  • [1] Co-regularized Alignment for Unsupervised Domain Adaptation
    Kumar, Abhishek
    Sattigeri, Prasanna
    Wadhawan, Kahini
    Karlinsky, Leonid
    Feris, Rogerio
    Freeman, William T.
    Wornell, Gregory
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [2] Robust graph regularized unsupervised feature selection
    Tang, Chang
    Zhu, Xinzhong
    Chen, Jiajia
    Wang, Pichao
    Liu, Xinwang
    Tian, Jie
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2018, 96 : 64 - 76
  • [3] Unsupervised feature selection by regularized matrix factorization
    Qi, Miao
    Wang, Ting
    Liu, Fucong
    Zhang, Baoxue
    Wang, Jianzhong
    Yi, Yugen
    [J]. NEUROCOMPUTING, 2018, 273 : 593 - 610
  • [4] PolSAR Image Feature Extraction via Co-Regularized Graph Embedding
    Huang, Xiayuan
    Nie, Xiangli
    Qiao, Hong
    [J]. REMOTE SENSING, 2020, 12 (11)
  • [5] Robust inner product regularized unsupervised feature selection
    Qian, Youcheng
    Yin, Xueyan
    Gao, Wei
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (23) : 33593 - 33615
  • [6] Unsupervised feature selection by regularized self-representation
    Zhu, Pengfei
    Zuo, Wangmeng
    Zhang, Lei
    Hu, Qinghua
    Shiu, Simon C. K.
    [J]. PATTERN RECOGNITION, 2015, 48 (02) : 438 - 446
  • [7] Robust inner product regularized unsupervised feature selection
    Youcheng Qian
    Xueyan Yin
    Wei Gao
    [J]. Multimedia Tools and Applications, 2019, 78 : 33593 - 33615
  • [8] Dual graph regularized compact feature representation for unsupervised feature selection
    Li, Shaoyong
    Tang, Chang
    Liu, Xinwang
    Liu, Yaping
    Chen, Jiajia
    [J]. NEUROCOMPUTING, 2019, 331 : 77 - 96
  • [9] Co-regularized kernel ensemble regression
    Wornyo, Dickson Keddy
    Shen, Xiang-Jun
    Dong, Yong
    Wang, Liangjun
    Huang, Shu-Cheng
    [J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2019, 22 (02): : 717 - 734
  • [10] Co-regularized kernel ensemble regression
    Dickson Keddy Wornyo
    Xiang-Jun Shen
    Yong Dong
    Liangjun Wang
    Shu-Cheng Huang
    [J]. World Wide Web, 2019, 22 : 717 - 734