Next Article in Journal
On the Performance of Interleavers for Quantum Turbo Codes
Next Article in Special Issue
Double-Granule Conditional-Entropies Based on Three-Level Granular Structures
Previous Article in Journal
Stationary-State Statistics of a Binary Neural Network Model with Quenched Disorder
Previous Article in Special Issue
A Maximum Entropy Procedure to Solve Likelihood Equations
Article

Model Selection for Non-Negative Tensor Factorization with Minimum Description Length

1
The Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku 113-8656, Japan
2
The Department of General Systems Studies, Graduate School of Arts and Sciences, The University of Tokyo, 3-8-1 Komaba, Meguro-ku 153-8902, Japan
*
Author to whom correspondence should be addressed.
Entropy 2019, 21(7), 632; https://doi.org/10.3390/e21070632
Received: 24 April 2019 / Revised: 14 June 2019 / Accepted: 23 June 2019 / Published: 27 June 2019
(This article belongs to the Special Issue Information-Theoretical Methods in Data Mining)
Non-negative tensor factorization (NTF) is a widely used multi-way analysis approach that factorizes a high-order non-negative data tensor into several non-negative factor matrices. In NTF, the non-negative rank has to be predetermined to specify the model and it greatly influences the factorized matrices. However, its value is conventionally determined by specialists’ insights or trial and error. This paper proposes a novel rank selection criterion for NTF on the basis of the minimum description length (MDL) principle. Our methodology is unique in that (1) we apply the MDL principle on tensor slices to overcome a problem caused by the imbalance between the number of elements in a data tensor and that in factor matrices, and (2) we employ the normalized maximum likelihood (NML) code-length for histogram densities. We employ synthetic and real data to empirically demonstrate that our method outperforms other criteria in terms of accuracies for estimating true ranks and for completing missing values. We further show that our method can produce ranks suitable for knowledge discovery. View Full-Text
Keywords: minimum description length; non-negative tensor factorization; model selection; normalized maximum likelihood code length minimum description length; non-negative tensor factorization; model selection; normalized maximum likelihood code length
Show Figures

Figure 1

MDPI and ACS Style

Fu, Y.; Matsushima, S.; Yamanishi, K. Model Selection for Non-Negative Tensor Factorization with Minimum Description Length. Entropy 2019, 21, 632. https://doi.org/10.3390/e21070632

AMA Style

Fu Y, Matsushima S, Yamanishi K. Model Selection for Non-Negative Tensor Factorization with Minimum Description Length. Entropy. 2019; 21(7):632. https://doi.org/10.3390/e21070632

Chicago/Turabian Style

Fu, Yunhui, Shin Matsushima, and Kenji Yamanishi. 2019. "Model Selection for Non-Negative Tensor Factorization with Minimum Description Length" Entropy 21, no. 7: 632. https://doi.org/10.3390/e21070632

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop