Online Matrix Factorization for Space Embedding Multilabel Annotation

  • Sebastian Otálora-Montenegro
  • Santiago A. Pérez-Rubiano
  • Fabio A. González
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8258)


The paper presents an online matrix factorization algorithm for multilabel learning. This method addresses the multi-label annotation problem finding a joint embedding that represents both instances and labels in a common latent space. An important characteristic of the novel method is its scalability, which is a consequence of its formulation as an online learning algorithm. The method was systematically evaluated in different standard datasets and compared against state-of-the-art space embedding multi-label learning algorithms showing competitive results.


Compressive Sensing Canonical Correlation Analysis Reconstruction Function Label Representation Online Learning Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Caicedo, J.C., González, F.A.: Multimodal fusion for image retrieval using matrix factorization. In: Proceedings of the 2nd ACM International Conference on Multimedia Retrieval, ICMR 2012, pp. 56:1–56:8. ACM, New York (2012)Google Scholar
  2. 2.
    Caicedo, J.C., González, F.A., Jaafar, B.-A., Olfa, N.: Multimodal Representation, Indexing, Automated Annotation and Retrieval of Image Collections via Non-negative Matrix Factorization. Neurocomputing 76(1) (2012)Google Scholar
  3. 3.
    Chen, Y.-N., Lin, H.-T.: Feature-aware label space dimension reduction for multi-label classification. In: Advances in Neural Information Processing Systems 25, pp. 1538–1546 (2012)Google Scholar
  4. 4.
    Hsu, D., Kakade, S.M., Langford, J., Zhang, T.: Multi-label prediction via compressed sensing. arXiv preprint arXiv:0902.1284 (2009)Google Scholar
  5. 5.
    Li, Z., Liu, J., Lu, H.: Structure preserving non-negative matrix factorization for dimensionality reduction. Computer Vision and Image Understanding 117(9), 1175–1189 (2013)CrossRefGoogle Scholar
  6. 6.
    Park, S., Choi, S.: Max-margin embedding for multi-label learning. Pattern Recognition Letters (2012)Google Scholar
  7. 7.
    Sun, L., Ji, S., Ye, J.: Canonical correlation analysis for multilabel classification: a least-squares formulation, extensions, and analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(1), 194–200 (2011)CrossRefGoogle Scholar
  8. 8.
    Tai, F., Lin, H.-T.: Multilabel classification with principal label space transformation. Neural Computation 24(9), 2508–2542 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Tsoumakas, G., Katakis, I., Vlahavas, I.: Mining multi-label data. In: Data Mining and Knowledge Discovery Handbook, pp. 667–685. Springer (2010)Google Scholar
  10. 10.
    Tsoumakas, G., Spyromitros-Xioufis, E., Vilcek, J., Vlahavas, I.: Mulan: A java library for multi-label learning. Journal of Machine Learning Research 12, 2411–2414 (2011)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sebastian Otálora-Montenegro
    • 1
  • Santiago A. Pérez-Rubiano
    • 1
  • Fabio A. González
    • 1
  1. 1.MindLab Research GroupUniversidad Nacional de ColombiaBogotáColombia

Personalised recommendations