TY  - CONF
AU  - Muzzarelli, Laura
AU  - Weis, Susanne
AU  - Eickhoff, Simon
AU  - Patil, Kaustubh
TI  - Rank Selection in Non-negative Matrix Factorization: systematic comparison and a new MAD metric
M1  - FZJ-2019-01911
SP  - 7
PY  - 2019
N1  - This study was partly supported by the Helmholtz Portfolio Theme "Supercomputing and Modeling for the Human Brain" and the European Union’s Horizon 2020 Research and Innovation Programme under Grant Agreement No. 785907 (HBP SGA2).
AB  - Abstract—Non-Negative Matrix Factorization (NMF) is a powerful dimensionality reduction and factorization method that provides a part-based representation of the data. In the absence of a priori knowledge about the latent dimensionality of the data, it is necessary to select a rank of the reduced representation. Several rank selection methods have been proposed, but no consensus exists on when a method is suitable to use. In this work, we propose a new metric for rank selection based on imputation cross-validation, and we systematically compare it against six other metrics while assessing the effects of data properties. Using synthetic datasets with different properties, our work critically evidences that most methods fail to identify the true rank. We show that properties of the data heavily impact the ability of different methods. Imputation-based metrics, including our new MADimput, provided the best accuracy irrespective of the data type, but no solution worked perfectly in all circumstances. One should therefore carefully assess characteristics of their dataset in order to identify the most suitable metric for rank selection. Keywords— non-negative matrix factorization, rank selection, cross-validation.
T2  - 2019 International Joint Conference on Neural Networks
CY  - 14 Jul 2019 - 19 Jul 2019, Budapest (Hungary)
Y2  - 14 Jul 2019 - 19 Jul 2019
M2  - Budapest, Hungary
LB  - PUB:(DE-HGF)8
UR  - https://juser.fz-juelich.de/record/861439
ER  -