skip to main content
10.1145/2487575.2487627acmconferencesArticle/Chapter ViewAbstractPublication PageskddConference Proceedingsconference-collections
research-article

Active learning and search on low-rank matrices

Published:11 August 2013Publication History

ABSTRACT

Collaborative prediction is a powerful technique, useful in domains from recommender systems to guiding the scientific discovery process. Low-rank matrix factorization is one of the most powerful tools for collaborative prediction. This work presents a general approach for active collaborative prediction with the Probabilistic Matrix Factorization model. Using variational approximations or Markov chain Monte Carlo sampling to estimate the posterior distribution over models, we can choose query points to maximize our understanding of the model, to best predict unknown elements of the data matrix, or to find as many "positive" data points as possible. We evaluate our methods on simulated data, and also show their applicability to movie ratings prediction and the discovery of drug-target interactions.

References

  1. R. P. Adams, G. E. Dahl, and I. Murray. Incorporating side information in probabilistic matrix factorization with Gaussian processes. 2010.Google ScholarGoogle Scholar
  2. C. Boutilier, R. S. Zemel, and B. Marlin. Active collaborative filtering. In UAI. Morgan Kaufmann Publishers Inc, 2002. Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. P. Dutilleul. The MLE algorithm for the matrix normal distribution. Journal of Statistical Computation and Simulation, 64(2):105--123, 1999.Google ScholarGoogle ScholarCross RefCross Ref
  4. A. Eriksson and A. Van Den Hengel. Efficient computation of robust low-rank matrix approximations in the presence of missing data using the L1 norm. CVPR, pages 771--778, 2010.Google ScholarGoogle Scholar
  5. R. Garnett, Y. Krishnamurthy, D. Wang, J. Schneider, and R. Mann. Bayesian Optimal Active Search on Graphs. In Ninth Workshop on Mining and Learning with Graphs, 2011.Google ScholarGoogle Scholar
  6. R. Garnett, Y. Krishnamurthy, X. Xiong, J. Schneider, and R. Mann. Bayesian optimal active search and surveying. In ICML, 2012.Google ScholarGoogle Scholar
  7. M. Gönen, S. A. Khan, and S. Kaski. Kernelized Bayesian matrix factorization. arXiv.org, stat.ML, 2012.Google ScholarGoogle Scholar
  8. M. D. Hoffman and A. Gelman. The no-U-turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo. Journal of Machine Learning Research, In press.Google ScholarGoogle Scholar
  9. T. Hofmann and J. Puzicha. Latent class models for collaborative filtering. International Joint Conference on Artificial Intelligence, 16:688--693, 1999. Google ScholarGoogle ScholarDigital LibraryDigital Library
  10. L. Isserlis. On a formula for the product-moment coefficient of any order of a normal frequency distribution in any number of variables. Biometrika, 12:134--139, 1918.Google ScholarGoogle ScholarCross RefCross Ref
  11. R. Jin and L. Si. A Bayesian approach toward active learning for collaborative filtering. UAI, pages 278--285, 2004. Google ScholarGoogle ScholarDigital LibraryDigital Library
  12. R. Karimi, C. Freudenthaler, A. Nanopoulos, and L. Schmidt-Thieme. Active learning for aspect model in recommender systems. IEEE Symposium on Computational Intelligence and Data Mining (CIDM), pages 162--167, 2011.Google ScholarGoogle ScholarCross RefCross Ref
  13. R. Karimi, C. Freudenthaler, A. Nanopoulos, and L. Schmidt-Thieme. Non-myopic active learning for recommender systems based on matrix factorization. Information Reuse and Integration (IRI), pages 299--303, 2011.Google ScholarGoogle ScholarCross RefCross Ref
  14. R. Karimi, C. Freudenthaler, A. Nanopoulos, and L. Schmidt-Thieme. Towards optimal active learning for matrix factorization in recommender systems. In Tools with Artificial Intelligence (ICTAI), pages 1069--1076, 2011. Google ScholarGoogle ScholarDigital LibraryDigital Library
  15. R. Karimi, C. Freudenthaler, A. Nanopoulos, and L. Schmidt-Thieme. Exploiting the characteristics of matrix factorization for active learning in recommender systems. In RecSys '12, 2012. Google ScholarGoogle ScholarDigital LibraryDigital Library
  16. C. Knox, V. Law, T. Jewison, P. Liu, S. Ly, A. Frolkis, A. Pon, K. Banco, C. Mak, V. Neveu, Y. Djoumbou, R. Eisner, A. C. Guo, and D. S. Wishart. DrugBank 3.0: a comprehensive resource for 'omics' research on drugs. Nucleic Acids Research, 39(Database):D1035-D1041, 2010.Google ScholarGoogle Scholar
  17. R. F. Murphy. An active role for machine learning in drug development. Nature Publishing Group, 7(6):327--330, 2011.Google ScholarGoogle Scholar
  18. R. M. Neal. MCMC using Hamiltonian dynamics. In S. Brooks, A. Gelman, G. L. Jones, and X.-L. Meng, editors, Handbook of Markov Chain Monte Carlo, Handbooks of Modern Statistical Methods. Chapman & Hall/CRC, 2011.Google ScholarGoogle ScholarCross RefCross Ref
  19. J. Rennie and N. Srebro. Fast maximum margin matrix factorization for collaborative prediction. In Proceedings of the 22nd International Conference on Machine Learning, pages 713--719. 2005. Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. F. Ricci, L. Rokach, B. Shapira, and P. Kantor. Recommender Systems Handbook. Springer, 2011. Google ScholarGoogle ScholarCross RefCross Ref
  21. I. Rish and G. Tesauro. Active collaborative prediction with maximum margin matrix factorization. Inform. Theory and App. Workshop, 2007.Google ScholarGoogle Scholar
  22. N. Rubens, D. Kaplan, and M. Sugiyama. Active learning in recommender systems. In P. Kantor, F. Ricci, L. Rokach, and B. Shapira, editors, Recommender Systems Handbook, pages 735--767. Springer, 2011.Google ScholarGoogle ScholarCross RefCross Ref
  23. R. Salakhutdinov and A. Mnih. Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. In ICML, pages 880--887, 2008. Google ScholarGoogle ScholarDigital LibraryDigital Library
  24. R. Salakhutdinov and A. Mnih. Probabilistic matrix factorization. In NIPS, 2008.Google ScholarGoogle ScholarDigital LibraryDigital Library
  25. H. Shan and A. Banerjee. Generalized probabilistic matrix factorizations for collaborative filtering. In ICDM, pages 1025--1030, 2010. Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. J. Silva and L. Carin. Active learning for online Bayesian matrix factorization. In KDD, 2012. Google ScholarGoogle ScholarDigital LibraryDigital Library
  27. N. Srebro, J. Rennie, and T. Jaakkola. Maximum-margin matrix factorization. In NIPS, volume 17, pages 1329--1336, 2005.Google ScholarGoogle Scholar
  28. Stan Development Team. Stan: A C library for probability and sampling, version 1.1, 2013.Google ScholarGoogle Scholar
  29. S. Tong and D. Koller. Support vector machine active learning with applications to text classification. Journal of Machine Learning Research, 2:45--66, 2002. Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. X. Yang, H. Steck, Y. Guo, and Y. Liu. On top-k recommendation using social networks. In RecSys '12, 2012. Google ScholarGoogle ScholarDigital LibraryDigital Library
  31. K. Yu, A. Schwaighofer, and V. Tresp. Collaborative ensemble learning: Combining collaborative and content-based information filtering via hierarchical Bayes. UAI, pages 616--623, 2002. Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. T. Zhou, H. Shan, A. Banerjee, and G. Sapiro. Kernelized probabilistic matrix factorization: Exploiting graphs and side information. In SIAM Data Mining, pages 403--414, 2012.Google ScholarGoogle Scholar

Index Terms

  1. Active learning and search on low-rank matrices

          Recommendations

          Comments

          Login options

          Check if you have access through your login credentials or your institution to get full access on this article.

          Sign in

          PDF Format

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader