Linked PARAFAC/CP Tensor Decomposition and Its Fast Implementation for Multi-block Tensor Analysis
In this paper we propose a new flexible group tensor analysis model called the linked CP tensor decomposition (LCPTD). The LCPTD method can decompose given multiple tensors into common factor matrices, individual factor matrices, and core tensors, simultaneously. We applied the Hierarchical Alternating Least Squares (HALS) algorithm to the LCPTD model; besides we impose additional constraints to obtain sparse and nonnegative factors. Furthermore, we conducted some experiments of this model to demonstrate its advantages over existing models.
KeywordsTensor decompositions of multi-block data PARAFAC/CP model Group Analysis Hierarchical Alternating Least Squares (HALS)
Unable to display preview. Download preview PDF.
- 1.Bro, R.: Multi-way analysis in the food industry - models, algorithms, and applications. Tech. rep., MRI, EPG and EMA, Proc. ICSLP 2000 (1998)Google Scholar
- 3.Cichocki, A.: Tensor decompositions: New concepts for brain data analysis? Journal of Control, Measurement, and System Integration (SICE) 7, 507–517 (2011)Google Scholar
- 4.Cichocki, A., Phan, A.: Fast local algorithms for large scale nonnegative matrix and tensor factorizations. IEICE Trans. Fundamentals of Electronics, Communications and Computer Sciences E92-A (3), 708–721 (2009)Google Scholar
- 6.Cichocki, A., Zdunek, R., Phan, A.H., Amari, S.: Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation. Wiley Publishing (2009)Google Scholar
- 8.Harshman, R.: Foundations of the parafac procedure: Model and conditions for an ’explanatory’ multi-mode factor analysis. UCLA Working Papers in phonetics 16, 1–84 (1970)Google Scholar
- 11.Lee, H., Choi, S.: Group nonnegative matrix factorization for EEG classification. Journal of Machine Learning Research - Proceedings Track 5, 320–327 (2009)Google Scholar