Online Projective Nonnegative Matrix Factorization for Large Datasets

  • Zhirong Yang
  • He Zhang
  • Erkki Oja
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7665)


Projective Nonnegative Matrix Factorization (PNMF) is one of the recent methods for computing low-rank approximations to data matrices. It is advantageous in many practical application domains such as clustering, graph partitioning, and sparse feature extraction. However, up to now a scalable implementation of PNMF for large-scale machine learning problems has been lacking. Here we provide an online algorithm for fast PNMF learning with low memory cost. The new algorithm simply applies multiplicative update rules iteratively on small subsets of the data, with historical data naturally accumulated. Consequently users do not need extra efforts to tune any optimization parameters such as learning rates or the history weight. In addition to scalability and convenience, empirical studies on synthetic and real-world datasets indicate that our online algorithm runs much faster than the existing batch version.


Online learning PNMF NMF large-scale datasets 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cichocki, A., Zdunek, R., Phan, A.H., Amari, S.: Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis. John Wiley (2009)Google Scholar
  2. 2.
    Ding, C., Li, T., Jordan, M.I.: Convex and semi-nonnegative matrix factorizations. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(1), 45–55 (2010)CrossRefGoogle Scholar
  3. 3.
    Févotte, C., Bertin, N., Durrieu, J.L.: Nonnegative matrix factorization with the Itakura-Saito divergence: with application to music analysis. Neural Computation 21(3), 793–830 (2009)zbMATHCrossRefGoogle Scholar
  4. 4.
    Kushner, H.J., Clark, D.S.: Stochastic Approximation Methods for Constrained and Unconstrained Systems. Springer, New York (1978)CrossRefGoogle Scholar
  5. 5.
    Lakshminarayanan, B., Raich, R.: Non-negative matrix factorization for parameter estimation in hidden markov models. In: Proceedings of IEEE International Workshop on Machine Learning for Signal Processing, pp. 89–94 (2010)Google Scholar
  6. 6.
    Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)CrossRefGoogle Scholar
  7. 7.
    Lin, C.J.: Projected gradient methods for non-negative matrix factorization. Neural Computation 19, 2756–2779 (2007)MathSciNetzbMATHCrossRefGoogle Scholar
  8. 8.
    Liu, C., Yang, H., Fan, J., He, L., Wang, Y.: Distributed nonnegative matrix factorization for web-scale dyadic data analysis on MapReduce. In: Proceedings of 19th International World Wide Web Conference (2010)Google Scholar
  9. 9.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online learning for matrix factorization and sparse coding. The Journal of Machine Learning Research 11, 19–60 (2010)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Phillips, P.J., Moon, H., Rizvi, S.A., Rauss, P.J.: The FERET evaluation methodology for face recognition algorithms. IEEE Trans. Pattern Analysis and Machine Intelligence 22, 1090–1104 (2000)CrossRefGoogle Scholar
  11. 11.
    Woodard, D., Flynn, P.: Finger surface as a biometric identifier. Computer Vision and Image Understanding 100(3), 357–384 (2005)CrossRefGoogle Scholar
  12. 12.
    Yang, Z., Oja, E.: Linear and nonlinear projective nonnegative matrix factorization. IEEE Transaction on Neural Networks 21(5), 734–749 (2010)CrossRefGoogle Scholar
  13. 13.
    Yang, Z., Oja, E.: Unified development of multiplicative algorithms for linear and quadratic nonnegative matrix factorization. IEEE Transactions on Neural Networks 22(12), 1878–1891 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Zhirong Yang
    • 1
  • He Zhang
    • 1
  • Erkki Oja
    • 1
  1. 1.Department of Information and Computer ScienceAalto University School of ScienceEspooFinland

Personalised recommendations