Abstract
NnmfPack is a library for the nonnegative matrix factorization (NNMF) problem. Nowadays NNMF is an essential tool in many fields spanning machine learning, data analysis, image analysis or audio source separation, among others. NnmfPack is an efficient numerical library conceived for shared memory heterogeneous parallel systems, and it supports, from its conception, both conventional multi-core processors and many-core coprocessors. In this article, NnmfPack is extended to handle different metrics options (\(\beta \)-divergence), and some other parallel algorithms have been added and tested. The performance of the new functionalities of NnmfPack is tested, and some precision results of the implementations are showed using an example borrowed from the image processing field.
Similar content being viewed by others
References
Battenberg E, Freed A, Wessel D (2010) Advances in the parallelization of music and audio applications. In: Proceedings of the International Computer Music Conference, New York
Wnag J, Zhong W, Zhang J (2006) NNMF-based factorization techniques for high-accuracy privacy protection on non-negative-valued datasets. In: Proceedings of the Sixth IEEE International Conference on Computing and Processing, Data Mining Workshops ICDM Workshops, pp 513–517
Rodriguez-Serrano FJ, Carabias-Orti JJ, Vera-Candeas P, Virtanen T, Ruiz-Reyes N (2012) Multiple instrument mixtures source separation evaluation using instrument-dependent NMF models. In: Proceedings of the 10th international conference on latent variable analysis and signal separation, March 12–15, Tel Aviv, Israel. LNCS, vol 7191. Springer, Berlin, pp 380–387
Xu W, Liu X, Gong Y (2003) Document clustering based on non-negative matrix factorization. In: Proceedings of the 26th annual international ACM SIGIR conference on research and development in information retrieval, July 28–Aug 1, Toronto, Canada, pp 267–273
Berry MW, Browne M, Langville A, Pauca V, Plemmons R (2007) Algorithms and applications for approximate nonnegative matrix factorization. Comput Stat Data Anal 52:155–173
Devajaran K (2008) Nonnegative matrix factorization: an analytical and interpretative tool in computational biology. PLoS Comput Biol 4(7):e1000029. doi:10.1371/journal.pcbi.1000029
Lee DD, Seung HS (2001) Algorithms for non-negative matrix factorization., Advances in neural information processing systemsMIT Press, Cambridge
Kim J, Park H (2008) Nonnegative matrix factorization based on alternating nonnegativity constrained least squares and active set method. SIAM J Matrix Anal Appl 30:713–730
Guan N, Tao D, Luo Z, Yuan B (2012) NeNMF: An optimal gradient method for non-negative matrix factorization. IEEE Trans Signal Process 60(6):2882–2898
Cichocki A, Phan AH (2009) Fast local algorithms for large scale nonnegative matrix and tensor factorizations. In: Proceedings of IEICE transactions on fundamentals of electronics communications and computer sciences, E92-A, pp 708–721
Cichocki A, Zdunek R, Amari SI (2007) Hierarchical ALS algorithms for nonnegative matrix and 3D tensor factorization. In: Proceedings of the 7th international conference on independent component analysis and signal separation, September 9–12, London, UK. LNCS, vol 4666. Springer, Berlin, pp 169–176
Alonso P, García VM, Martínez-Zaldívar FJ, Salazar A, Vergara L, Vidal AM (2014) Parallel approach to NNMF on multicore architecture. J Supercomput. 70(2):564–576
Díaz-Gracia N, Cocaña-Fernández A, Alonso-González M, Martínez-Zaldívar FJ, Cortina R, García-Mollá VM, Alonso P, Ranilla J, Vidal AM (2014) NNMFPACK: a versatile approach to an NNMF parallel library. In: Proceedings of the 2014 international conference on computational and mathematical methods in science and engineering, Cádiz, 2014, pp 456–465
Carabias-Orti JJ, Rodriguez-Serrano FJ, Vera-Candeas P, Cañadas-Quesada FJ, Ruiz-Reyes N (2013) Constrained non-negative sparse coding using learnt instrument templates for real time music transcription. Eng Appl AI 26(7):1671–1680
Carabias-Orti JJ, Virtanen T, Vera-Candeas P, Ruiz-Reyes N, Cañadas-Quesada FJ (2011) Musical instrument sound multi-excitation model for non-negative spectrogram factorization. IEEE J Select Topics Signal Process 5(6):1144–1158
Minami M, Eguchi S (2002) Robust blind source separation by beta-divergence. Neural Comput 14:1859–1886
Févotte C, Bertin N, Durrieu J-L (2009) Nonnegative matrix factorization with the Itakura-Saito divergence: with application to music analysis. Neural Comput 21:793–830
Golub GH, Van Loan CF (1996) Matrix Comput. Johns Hopkins University Press, Baltimore
Acknowledgments
This work has been partially supported by “Ministerio de Economía y Competitividad” from Spain, under the projects TEC2012-38142-C04-01 and TEC2012-38142-C04-04 and by ISIC/2012/006 and PROMETEO FASE II 2014/003 projects of Generalitat Valenciana.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Díaz-Gracia, N., Cocaña-Fernández, A., Alonso-González, M. et al. Improving NNMFPACK with heterogeneous and efficient kernels for \(\beta \)-divergence metrics. J Supercomput 71, 1846–1856 (2015). https://doi.org/10.1007/s11227-014-1363-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-014-1363-y