Controlling sparseness in non-negative tensor factorization

被引：0
|
作者：
Heiler, M [1 ]
Schnörr, C [1 ]
机构：
[1] Univ Mannheim, Dept Math & Comp Sci, Comp Vis Graph & Pattern Recognit Grp, D-68131 Mannheim, Germany
来源：
COMPUTER VISION - ECCV 2006 , PT 1, PROCEEDINGS | 2006年 / 3951卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Non-negative tenser factorization (NTF) has recently been proposed as sparse and efficient image representation (Welling and Weber, Patt. Rec. Let., 2001). Until now, sparsity of the tensor factorization has been empirically observed in many cases, but there was no systematic way to control it. In this work, we show that a sparsity measure recently proposed for non-negative matrix factorization (Hoyer, J. Mach. Learn. Res., 2004) applies to NTF and allows precise control over sparseness of the resulting factorization. We devise an algorithm based on sequential conic programming and show improved performance over classical NTF codes on artificial and on real-world data sets.
引用
收藏
页码：56 / 67
页数：12
相关论文
共 50 条
  • [1] Non-negative matrix factorization with sparseness constraints
    Hoyer, PO
    JOURNAL OF MACHINE LEARNING RESEARCH, 2004, 5 : 1457 - 1469
  • [2] Non-negative Multiple Tensor Factorization
    Takeuchi, Koh
    Tomioka, Ryota
    Ishiguro, Katsuhiko
    Kimura, Akisato
    Sawada, Hiroshi
    2013 IEEE 13TH INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2013, : 1199 - 1204
  • [3] Non-negative tensor factorization using α and β divergences
    Cichocki, Andrzej
    Zdunek, Rafal
    Choi, Seungjin
    Plemmons, Robert
    Amari, Shun-ichi
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL III, PTS 1-3, PROCEEDINGS, 2007, : 1393 - +
  • [4] CitySpectrum: A Non-negative Tensor Factorization Approach
    Fan, Zipei
    Song, Xuan
    Shibasaki, Ryosuke
    UBICOMP'14: PROCEEDINGS OF THE 2014 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING, 2014, : 213 - 223
  • [5] Non-negative Tensor Factorization for Speech Enhancement
    He, Liang
    Zhang, Weiqiang
    Shi, Mengnan
    PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE: TECHNOLOGIES AND APPLICATIONS, 2016, 127
  • [6] Automatic Non-negative Matrix Factorization Clustering with Competitive Sparseness Constraints
    Liu, Chenglin
    Ma, Jinwen
    INTELLIGENT COMPUTING METHODOLOGIES, 2014, 8589 : 118 - 125
  • [7] Non-Negative Matrix Factorization With Sparseness Constraints For Credit Risk Assessment
    Liu, Yulong
    Du, Jianlei
    Wang, Feng
    PROCEEDINGS OF 2013 IEEE INTERNATIONAL CONFERENCE ON GREY SYSTEMS AND INTELLIGENT SERVICES (GSIS), 2013, : 211 - 214
  • [8] FacetCube: a general framework for non-negative tensor factorization
    Chi, Yun
    Zhu, Shenghuo
    KNOWLEDGE AND INFORMATION SYSTEMS, 2013, 37 (01) : 155 - 179
  • [9] FacetCube: a general framework for non-negative tensor factorization
    Yun Chi
    Shenghuo Zhu
    Knowledge and Information Systems, 2013, 37 : 155 - 179
  • [10] CONSTRAINT NON-NEGATIVE MATRIX FACTORIZATION WITH SPARSENESS AND PIECEWISE SMOOTHNESS FOR HYPERSPECTRAL UNMIXING
    Sun, Xu
    Peng, Qian
    Zhang, Bing
    Gao, Lianru
    Yang, Lina
    2018 9TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS), 2018,
12345