Non-negative sub-tensor ensemble factorization (NsTEF) algorithm. A new incremental tensor factorization for large data sets

被引：5
作者：
Vigneron, Vincent [1 ]
Kodewitz, Andreas [1 ]
da Costa, Michele Nazareth [2 ]
Tome, Ana Maria [3 ]
Langlang, Elmar [4 ]
机构：
[1] Univ Paris Saclay, Univ Ewy, IBISC, F-91025 Evry, France
[2] Univ Campinas UNICAMP, DSPCom Lab, POB 6101, BR-13083852 Campinas, SP, Brazil
[3] Univ Aveiro, Dept Elect Telecomunicacoes & Informat, Aveiro, Portugal
[4] Univ Regensburg, Inst Biophys & Phys Biochem, Univ Str 31, D-93040 Regensburg, Germany
来源：
SIGNAL PROCESSING | 2018年 / 144卷
基金：
巴西圣保罗研究基金会;
关键词：
Non-negative tensor decomposition; CANDECOMP/PARAFAC Decomposition; Matrix factorization; NTF; Incremental algorithm; Learning method; MATRIX FACTORIZATION; CANONICAL DECOMPOSITION; UNIQUENESS; CANDECOMP/PARAFAC; CLASSIFICATION; RECOGNITION; MODE;
D O I：
10.1016/j.sigpro.2017.09.012
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In this work we present a novel algorithm for nonnegative tensor factorization (NTF). Standard NTF algorithms are very restricted in the size of tensors that can be decomposed. Our algorithm overcomes this size restriction by interpreting the tensor as a set of sub-tensors and by proceeding the decomposition of sub-tensor by sub-tensor. This approach requires only one sub-tensor at once to be available in memory. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码：77 / 86
页数：10
相关论文
共 69 条
[1]  
[Anonymous], 1970, UCLA Working Papers in Phonetics, DOI DOI 10.1134/S0036023613040165
[2]  
[Anonymous], 2009, NONNEGATIVE MATRIX T
[3]  
[Anonymous], 1998, MODELS ALGORITHMS
[4]  
[Anonymous], 1989, Multiway data analysis
[5]   Algorithms and applications for approximate nonnegative matrix factorization [J].
Berry, Michael W. ;
Browne, Murray ;
Langville, Amy N. ;
Pauca, V. Paul ;
Plemmons, Robert J. .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2007, 52 (01) :155-173
[6]   Incremental subspace learning via non-negative matrix factorization [J].
Bucak, Serhat S. ;
Gunsel, Bilge .
PATTERN RECOGNITION, 2009, 42 (05) :788-797
[7]   ANALYSIS OF INDIVIDUAL DIFFERENCES IN MULTIDIMENSIONAL SCALING VIA AN N-WAY GENERALIZATION OF ECKART-YOUNG DECOMPOSITION [J].
CARROLL, JD ;
CHANG, JJ .
PSYCHOMETRIKA, 1970, 35 (03) :283-&
[8]  
Chen J., 2014, IEEE T SIGNAL PROCES, V62
[9]  
Cichocki A, 2006, LECT NOTES COMPUT SC, V3889, P32
[10]  
Cichocki A., 2009, IEICE T FUND ELECTR, VE92-A, P1
1234567