A Provable Splitting Approach for Symmetric Nonnegative Matrix Factorization

被引:4
|
作者
Li, Xiao [1 ,2 ]
Zhu, Zhihui [3 ]
Li, Qiuwei [4 ]
Liu, Kai [5 ]
机构
[1] Chinese Univ Hong Kong, Sch Data Sci, Shenzhen 518172, Guangdong, Peoples R China
[2] Shenzhen Inst Artificial Intelligence & Robot Soc, Shenzhen, Guangdong, Peoples R China
[3] Univ Denver, Dept Elect & Comp Engn, Denver, CO 80208 USA
[4] Alibaba Grp, Damo Acad, Decis Intelligence Lab, Bellevue, WA 98004 USA
[5] Clemson Univ, Comp Sci Div, Clemson, SC 29634 USA
基金
中国国家自然科学基金;
关键词
Convergence; Symmetric matrices; Signal processing algorithms; Clustering algorithms; Minimization; Transforms; Optimization; Symmetric nonnegative matrix factorization; convergence; image clustering; alternating minimization; CONVERGENCE ANALYSIS; ALGORITHMS; NONCONVEX; MINIMIZATION; DESCENT;
D O I
10.1109/TKDE.2021.3125947
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The symmetric Nonnegative Matrix Factorization (NMF), a special but important class of the general NMF, has found numerous applications in data analysis such as various clustering tasks. Unfortunately, designing fast algorithms for the symmetric NMF is not as easy as for its nonsymmetric counterpart, since the latter admits the splitting property that allows state-of-the-art alternating-type algorithms. To overcome this issue, we first split the decision variable and transform the symmetric NMF to a penalized nonsymmetric one, paving the way for designing efficient alternating-type algorithms. We then show that solving the penalized nonsymmetric reformulation returns a solution to the original symmetric NMF. Moreover, we design a family of alternating-type algorithms and show that they all admit strong convergence guarantee: the generated sequence of iterates is convergent and converges at least sublinearly to a critical point of the original symmetric NMF. Finally, we conduct experiments on both synthetic data and real image clustering to support our theoretical results and demonstrate the performance of the alternating-type algorithms.
引用
收藏
页码:2206 / 2219
页数:14
相关论文
共 50 条
  • [1] A Stochastic Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization
    Lu, Songtao
    Hong, Mingyi
    Wang, Zhengdao
    [J]. ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 54, 2017, 54 : 812 - 821
  • [2] A Collaborative Neurodynamic Approach to Symmetric Nonnegative Matrix Factorization
    Che, Hangjun
    Wang, Jun
    [J]. NEURAL INFORMATION PROCESSING (ICONIP 2018), PT II, 2018, 11302 : 453 - 462
  • [3] Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization
    Ibrahim, Shahana
    Fu, Xiao
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [4] An Overlapping Community Detection Approach in Ego-Splitting Networks Using Symmetric Nonnegative Matrix Factorization
    Huang, Mingqing
    Jiang, Qingshan
    Qu, Qiang
    Rasool, Abdur
    [J]. SYMMETRY-BASEL, 2021, 13 (05):
  • [5] A NONCONVEX SPLITTING METHOD FOR SYMMETRIC NONNEGATIVE MATRIX FACTORIZATION: CONVERGENCE ANALYSIS AND OPTIMALITY
    Lu, Songtao
    Hong, Mingyi
    Wang, Zhengdao
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 2572 - 2576
  • [6] A Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization: Convergence Analysis and Optimality
    Lu, Songtao
    Hong, Mingyi
    Wang, Zhengdao
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2017, 65 (12) : 3120 - 3135
  • [7] On reduced rank nonnegative matrix factorization for symmetric nonnegative matrices
    Catral, M
    Han, LX
    Neumann, M
    Plemmons, RJ
    [J]. LINEAR ALGEBRA AND ITS APPLICATIONS, 2004, 393 : 107 - 126
  • [8] Symmetric nonnegative matrix factorization: A systematic review
    Chen, Wen-Sheng
    Xie, Kexin
    Liu, Rui
    Pan, Binbin
    [J]. NEUROCOMPUTING, 2023, 557
  • [9] A multilevel approach for nonnegative matrix factorization
    Gillis, Nicolas
    Glineur, Francois
    [J]. JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2012, 236 (07) : 1708 - 1723
  • [10] A PROJECTIVE APPROACH TO NONNEGATIVE MATRIX FACTORIZATION
    Groetzner, Patrick
    [J]. ELECTRONIC JOURNAL OF LINEAR ALGEBRA, 2021, 37 : 583 - 597