Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection

被引:278
|
作者
Li, Zechao [1 ]
Liu, Jing [2 ]
Yang, Yi [3 ]
Zhou, Xiaofang [3 ]
Lu, Hanqing [2 ]
机构
[1] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Jiangsu, Peoples R China
[2] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
[3] Univ Queensland, Sch Informat Technol & Elect Engn, Brisbane, Qld 4072, Australia
基金
中国国家自然科学基金;
关键词
Feature selection; nonnegative spectral clustering; latent structure; row-sparsity; IMAGE ANNOTATION; CLASSIFICATION; FRAMEWORK;
D O I
10.1109/TKDE.2013.65
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many pattern analysis and data mining problems have witnessed high-dimensional data represented by a large number of features, which are often redundant and noisy. Feature selection is one main technique for dimensionality reduction that involves identifying a subset of the most useful features. In this paper, a novel unsupervised feature selection algorithm, named clustering-guided sparse structural learning (CGSSL), is proposed by integrating cluster analysis and sparse structural analysis into a joint framework and experimentally evaluated. Nonnegative spectral clustering is developed to learn more accurate cluster labels of the input samples, which guide feature selection simultaneously. Meanwhile, the cluster labels are also predicted by exploiting the hidden structure shared by different features, which can uncover feature correlations to make the results more reliable. Row-wise sparse models are leveraged to make the proposed model suitable for feature selection. To optimize the proposed formulation, we propose an efficient iterative algorithm. Finally, extensive experiments are conducted on 12 diverse benchmarks, including face data, handwritten digit data, document data, and biomedical data. The encouraging experimental results in comparison with several representative algorithms and the theoretical analysis demonstrate the efficiency and effectiveness of the proposed algorithm for feature selection.
引用
收藏
页码:2138 / 2150
页数:13
相关论文
共 50 条
  • [21] Dictionary learning for unsupervised feature selection via dual sparse regression
    Wu, Jian-Sheng
    Liu, Jing-Xin
    Wu, Jun-Yun
    Huang, Wei
    APPLIED INTELLIGENCE, 2023, 53 (15) : 18840 - 18856
  • [22] Dictionary learning for unsupervised feature selection via dual sparse regression
    Jian-Sheng Wu
    Jing-Xin Liu
    Jun-Yun Wu
    Wei Huang
    Applied Intelligence, 2023, 53 : 18840 - 18856
  • [23] Unsupervised feature selection algorithm based on redundancy learning and sparse regression
    Kong, Guoping
    Ma, Yingcang
    Xing, Zhiwei
    Xin, Xiaolong
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2023, 625
  • [24] Joint Embedding Learning and Sparse Regression: A Framework for Unsupervised Feature Selection
    Hou, Chenping
    Nie, Feiping
    Li, Xuelong
    Yi, Dongyun
    Wu, Yi
    IEEE TRANSACTIONS ON CYBERNETICS, 2014, 44 (06) : 793 - 804
  • [25] Discriminative sparse subspace learning and its application to unsupervised feature selection
    Zhou, Nan
    Cheng, Hong
    Pedrycz, Witold
    Zhang, Yong
    Liu, Huaping
    ISA TRANSACTIONS, 2016, 61 : 104 - 118
  • [26] Unsupervised feature selection for balanced clustering
    Zhou, Peng
    Chen, Jiangyong
    Fan, Mingyu
    Du, Liang
    Shen, Yi-Dong
    Li, Xuejun
    KNOWLEDGE-BASED SYSTEMS, 2020, 193
  • [27] Pairwise Constraint-Guided Sparse Learning for Feature Selection
    Liu, Mingxia
    Zhang, Daoqiang
    IEEE TRANSACTIONS ON CYBERNETICS, 2016, 46 (01) : 298 - 310
  • [28] Clustering-Guided Twin Contrastive Learning for Endomicroscopy Image Classification
    Zhou, Jingjun
    Dong, Xiangjiang
    Liu, Qian
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (05) : 2879 - 2890
  • [29] An Unsupervised Attribute Clustering Algorithm for Unsupervised Feature Selection
    Zhou, Pei-Yuan
    Chan, Keith C. C.
    PROCEEDINGS OF THE 2015 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (IEEE DSAA 2015), 2015, : 710 - 716
  • [30] Dependence Guided Unsupervised Feature Selection
    Guo, Jun
    Zhu, Wenwu
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 2232 - 2239