Anchor Graph-Based Feature Selection for One-Step Multi-View Clustering

被引:4
作者
Zhao, Wenhui [1 ]
Li, Qin [2 ]
Xu, Huafu [3 ]
Gao, Quanxue [1 ]
Wang, Qianqian [1 ]
Gao, Xinbo [4 ]
机构
[1] Xidian Univ, Sch Telecommun Engn, Xian, 710071, Peoples R China
[2] Shenzhen Inst Informat Technol, Sch Software Engn, Shenzhen 518172, Peoples R China
[3] Informat Ctr Guangxi Zhuang Autonomous Reg, Guangxi Key Lab Digital Infrastruct, Nanning 530000, Peoples R China
[4] Chongqing Univ Posts & Telecommun, Chongqing Key Lab Image Cognit, Chongqing 400065, Peoples R China
基金
中国国家自然科学基金;
关键词
Multi-view clustering; feature selection; sparse representation; RANK;
D O I
10.1109/TMM.2024.3367605
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recently, multi-view clustering methods have been widely used in handling multi-media data and have achieved impressive performances. Among the many multi-view clustering methods, anchor graph-based multi-view clustering has been proven to be highly efficient for large-scale data processing. However, most existing anchor graph-based clustering methods necessitate post-processing to obtain clustering labels and are unable to effectively utilize the information within anchor graphs. To address this issue, we draw inspiration from regression and feature selection to propose Anchor Graph-Based Feature Selection for One-Step Multi-View Clustering (AGFS-OMVC). Our method combines embedding learning and sparse constraint to perform feature selection, allowing us to remove noisy anchor points and redundant connections in the anchor graph. This results in a clean anchor graph that can be projected into the label space, enabling us to obtain clustering labels in a single step without post-processing. Lastly, we employ the tensor Schatten $p$-norm as a tensor rank approximation function to capture the complementary information between different views, ensuring similarity between cluster assignment matrices. Experimental results on five real-world datasets demonstrate that our proposed method outperforms state-of-the-art approaches.
引用
收藏
页码:7413 / 7425
页数:13
相关论文
共 52 条
  • [11] Enhanced Tensor RPCA and its Application
    Gao, Quanxue
    Zhang, Pu
    Xia, Wei
    Xie, Deyan
    Gao, Xinbo
    Tao, Dacheng
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (06) : 2133 - 2140
  • [12] Multi-view spectral clustering via integrating nonnegative embedding and spectral embedding
    Hu, Zhanxuan
    Nie, Feiping
    Wang, Rong
    Li, Xuelong
    [J]. INFORMATION FUSION, 2020, 55 : 251 - 259
  • [13] Social Trust Prediction Using Heterogeneous Networks
    Huang, Jin
    Nie, Feiping
    Huang, Heng
    Tu, Yi-Cheng
    Lei, Yu
    [J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2013, 7 (04)
  • [14] Kang Z, 2020, AAAI CONF ARTIF INTE, V34, P4412
  • [15] Kumar A., 2011, P ADV NEUR INF PROC, P1413
  • [16] Kumar A., 2011, P 28 INT C MACH LEAR, P393, DOI [DOI 10.5555/3104482.3104532, 10.5555/3104482.3104532]
  • [17] Lee DD, 2001, ADV NEUR IN, V13, P556
  • [18] Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
    Li Fei-Fei
    Fergus, Rob
    Perona, Pietro
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2007, 106 (01) : 59 - 70
  • [19] Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method
    Li, Xuelong
    Zhang, Han
    Wang, Rong
    Nie, Feiping
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (01) : 330 - 344
  • [20] Li XL, 2017, IEEE T CYBERNETICS, V47, P3840, DOI 10.1109/TCYB.2016.2585355