Low-rank kernel learning for graph-based clustering

被引:138
作者
Kang, Zhao [1 ]
Wen, Liangjian [1 ]
Chen, Wenyu [1 ]
Xu, Zenglin [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 611731, Sichuan, Peoples R China
基金
中国博士后科学基金;
关键词
Low-rank kernel matrix; Graph construction; Multiple kernel learning; Clustering; Noise;
D O I
10.1016/j.knosys.2018.09.009
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determined by the chosen kernel matrix. To address this issue, previous multiple kernel learning algorithm has been applied to learn an optimal kernel from a group of predefined kernels. This approach might be sensitive to noise and limits the representation ability of the consensus kernel. In contrast to existing methods, we propose to learn a low-rank kernel matrix which exploits the similarity nature of the kernel matrix and seeks an optimal kernel from the neighborhood of candidate kernels. By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other. Extensive experimental results validate the efficacy of the proposed method. (C) 2018 Elsevier B.V. All rights reserved.
引用
收藏
页码:510 / 517
页数:8
相关论文
共 50 条
  • [21] Discriminative Low-Rank Representation for HSI Clustering
    Li, Zhixin
    Han, Bo
    Jia, Yuheng
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21
  • [22] Exemplar-based low-rank matrix decomposition for data clustering
    Lijun Wang
    Ming Dong
    [J]. Data Mining and Knowledge Discovery, 2015, 29 : 324 - 357
  • [23] Exemplar-based low-rank matrix decomposition for data clustering
    Wang, Lijun
    Dong, Ming
    [J]. DATA MINING AND KNOWLEDGE DISCOVERY, 2015, 29 (02) : 324 - 357
  • [24] GRAPH-REGULARIZED FAST LOW-RANK MATRIX APPROXIMATION USING THE NYSTROM METHOD FOR CLUSTERING
    Lee, Jieun
    Choe, Yoonsik
    [J]. 2018 IEEE 28TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2018,
  • [25] Non-Negative Symmetric Low-Rank Representation Graph Regularized Method for Cancer Clustering Based on Score Function
    Lu, Conghai
    Wang, Juan
    Liu, Jinxing
    Zheng, Chunhou
    Kong, Xiangzhen
    Zhang, Xiaofeng
    [J]. FRONTIERS IN GENETICS, 2020, 10
  • [26] Graph-based hierarchical conceptual clustering
    Jonyer, I
    Cook, DJ
    Holder, LB
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2002, 2 (01) : 19 - 43
  • [27] Graph-based Medical Image Clustering
    Li, Jian
    Pan, Haiwei
    Zhang, Minghui
    Han, Qilong
    Feng, Xiaoning
    [J]. 2012 8TH INTERNATIONAL CONFERENCE ON COMPUTING AND NETWORKING TECHNOLOGY (ICCNT, INC, ICCIS AND ICMIC), 2012, : 153 - 158
  • [28] Graph-based Multi-view Binary Learning for image clustering
    Jiang, Guangqi
    Wang, Huibing
    Peng, Jinjia
    Chen, Dongyan
    Fu, Xianping
    [J]. NEUROCOMPUTING, 2021, 427 : 225 - 237
  • [29] Joint enhanced low-rank constraint and kernel rank-order distance metric for low level vision processing
    Guo, Li
    Zhang, Xiaoqian
    Wang, Qian
    Xue, Xuqian
    Liu, Zhigui
    Mu, Yongfeng
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2022, 201
  • [30] Speech enhancement method based on low-rank approximation in a reproducing kernel Hilbert space
    Zhao, Yanping
    Qiu, Robert Caiming
    Zhao, Xiaohui
    Wang, Bo
    [J]. APPLIED ACOUSTICS, 2016, 112 : 79 - 83