Hauptseite > Publikationsdatenbank > Rank Selection in Non-negative Matrix Factorization: systematic comparison and a new MAD metric > print

001     865858
005     20210130003202.0
024 7 _ |a 10.1109/IJCNN.2019.8852146
|2 doi
024 7 _ |a altmetric:69028841
|2 altmetric
037 _ _ |a FZJ-2019-05146
100 1 _ |a Muzzarelli, Laura
|0 P:(DE-Juel1)173704
|b 0
|e Corresponding author
|u fzj
111 2 _ |a 2019 International Joint Conference on Neural Networks (IJCNN)
|c Budapest
|d 2019-07-14 - 2019-07-19
|w Hungary
245 _ _ |a Rank Selection in Non-negative Matrix Factorization: systematic comparison and a new MAD metric
260 _ _ |c 2019
|b IEEE
300 _ _ |a 8
336 7 _ |a CONFERENCE_PAPER
|2 ORCID
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a conferenceObject
|2 DRIVER
336 7 _ |a Output Types/Conference Paper
|2 DataCite
336 7 _ |a Contribution to a conference proceedings
|b contrib
|m contrib
|0 PUB:(DE-HGF)8
|s 1573822801_22185
|2 PUB:(DE-HGF)
500 _ _ |a This study was partly supported by the Helmholtz Portfolio Theme"Supercomputing and Modeling for the Human Brain" and the EuropeanUnion’s Horizon 2020 Research and Innovation Programme under GrantAgreement No. 785907 (HBP SGA2).
520 _ _ |a Non-Negative Matrix Factorization (NMF) is apowerful dimensionality reduction and factorization method thatprovides a part-based representation of the data. In the absence ofa priori knowledge about the latent dimensionality of the data, itis necessary to select a rank of the reduced representation. Severalrank selection methods have been proposed, but no consensusexists on when a method is suitable to use. In this work, we proposea new metric for rank selection based on imputation crossvalidation,and we systematically compare it against six othermetrics while assessing the effects of data properties. Usingsynthetic datasets with different properties, our work criticallyevidences that most methods fail to identify the true rank. Weshow that properties of the data heavily impact the ability ofdifferent methods. Imputation-based metrics, including our newMADimput, provided the best accuracy irrespective of the datatype, but no solution worked perfectly in all circumstances. Oneshould therefore carefully assess characteristics of their dataset inorder to identify the most suitable metric for rank selection.
536 _ _ |a 574 - Theory, modelling and simulation (POF3-574)
|0 G:(DE-HGF)POF3-574
|c POF3-574
|f POF III
|x 0
536 _ _ |a HBP SGA2 - Human Brain Project Specific Grant Agreement 2 (785907)
|0 G:(EU-Grant)785907
|c 785907
|f H2020-SGA-FETFLAG-HBP-2017
|x 1
588 _ _ |a Dataset connected to CrossRef Conference
700 1 _ |a Weis, Susanne
|0 P:(DE-Juel1)172811
|b 1
|u fzj
700 1 _ |a Eickhoff, Simon B.
|0 P:(DE-Juel1)131678
|b 2
|u fzj
700 1 _ |a Patil, Kaustubh R.
|0 P:(DE-Juel1)172843
|b 3
|u fzj
773 _ _ |a 10.1109/IJCNN.2019.8852146
856 4 _ |u https://juser.fz-juelich.de/record/865858/files/Muzzarelli19.pdf
|y Restricted
856 4 _ |u https://juser.fz-juelich.de/record/865858/files/Muzzarelli19.pdf?subformat=pdfa
|x pdfa
|y Restricted
909 C O |o oai:juser.fz-juelich.de:865858
|p openaire
|p VDB
|p ec_fundedresources
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-Juel1)173704
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 1
|6 P:(DE-Juel1)172811
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 2
|6 P:(DE-Juel1)131678
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 3
|6 P:(DE-Juel1)172843
913 1 _ |a DE-HGF
|b Key Technologies
|l Decoding the Human Brain
|1 G:(DE-HGF)POF3-570
|0 G:(DE-HGF)POF3-574
|2 G:(DE-HGF)POF3-500
|v Theory, modelling and simulation
|x 0
|4 G:(DE-HGF)POF
|3 G:(DE-HGF)POF3
914 1 _ |y 2019
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)INM-7-20090406
|k INM-7
|l Gehirn & Verhalten
|x 0
980 _ _ |a contrib
980 _ _ |a VDB
980 _ _ |a I:(DE-Juel1)INM-7-20090406
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21