Advertisement

User Modeling and User-Adapted Interaction

, Volume 25, Issue 1, pp 39–64 | Cite as

A supervised active learning framework for recommender systems based on decision trees

  • Rasoul KarimiEmail author
  • Alexandros Nanopoulos
  • Lars Schmidt-Thieme
Article

Abstract

A key challenge in recommender systems is how to profile new users. A well-known solution for this problem is to ask new users to rate a few items to reveal their preferences and to use active learning to find optimally informative items. Compared to the application of active learning in classification (regression), active learning in recommender systems presents several differences: although there are no ratings for new users, there is an abundance of available ratings—collectively—from past (existing) users. In this paper, we propose an innovative approach for active learning in recommender systems, which aims at taking advantage of this additional information. The main idea is to consider existing users as (hypothetical) new users and solve an active learning problem for each of them. In the end, we aggregate all solved problems in order to learn how to solve the active learning problem for a real new user. As the ratings of existing users (i.e., labels) are known and are used for active learning purposes, the proposed framework is in fact a supervised active learning framework. Based on this framework, we investigate two different types of models: the first model is based on information about average item ratings and the second on matrix factorization. We present experimental results on the Netflix dataset, which show that the proposed approach significantly outperforms state-of-the-art baselines.

Keywords

Active learning Recommender systems Cold-start problem  Matrix factorization 

References

  1. Adomavicius, G., Tuzhilin, A.: Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans. Knowl. Data Eng. 17(6), 734–749 (2005)CrossRefGoogle Scholar
  2. Boutilier, C., Zemel, R.S., Marlin, B.: Active collaborative filtering. In: Proceedings of the Nineteenth Annual Conference on Uncertainty in Artificial Intelligence, pp. 98–106. Acapulco, Mexico (2003)Google Scholar
  3. Burke, R.: Hybrid recommender systems. User Model. User Adapt. Interact. 12(4), 331–370 (2002)CrossRefzbMATHGoogle Scholar
  4. Chen, T., Li, H., Yang, Q., Yu, Y.: General functional matrix factorization using gradient boosting. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), JMLR Workshop and Conference Proceedings, vol., 28, pp. 436–444 (2013)Google Scholar
  5. Cohn, D.A., Ghahramani, Z., Jordan, M.I.: Active learning with statistical models. J. Artif. Int. Res. 4(1), 129–145 (1996)zbMATHGoogle Scholar
  6. Deodhar, M., Ghosh, J., Saar-Tsechansky, M.: Active learning for recommender systems with multiple localized models. In: Proceedings of the Fifth Symposium on Statistical Challenges in Electronic Commerce Research (2009)Google Scholar
  7. Elahi, M., Ricci, F., Rubens, N.: Adapting to natural rating acquisition with combined active learning strategies. In: Proceedings of the 20th International Conference on Foundations of Intelligent Systems (ISMIS’12), pp. 254–263. Springer-Verlag, Berlin (2012)Google Scholar
  8. Elahi, M., Braunhofer, M., Ricci, F., Tkalcic, M.: Personality-based active learning for collaborative filtering recommender systems. In: AI*IA, Springer, Lecture Notes in Computer Science, vol. 8249, pp. 360–371 (2013)Google Scholar
  9. Elahi, M., Ricci, F., Rubens, N.: Active learning strategies for rating elicitation in collaborative filtering: a system-wide perspective. ACM Trans. Intell. Syst. Technol. 5(1), 13:1–13:33 (2014)Google Scholar
  10. Gantner, Z., Drumond, L., Freudenthaler, C., Rendle, S., Schmidt-Thieme, L.: Learning attribute-to-feature mappings for cold-start recommendations. In: Proceedings of the 2010 IEEE International Conference on Data Mining, IEEE Computer Society (ICDM ’10), Washington, DC, USA, pp. 176–185 (2010)Google Scholar
  11. Golbandi, N., Koren, Y., Lempel, R.: Adaptive bootstrapping of recommender systems using decision trees. In: WSDM, pp. 595–604. ACM, New York (2011)Google Scholar
  12. Gunawardana, A., Meek, C.: Tied boltzmann machines for cold start recommendations. In: Proceedings of the 2008 ACM Conference on Recommender Systems (RecSys ’08), pp. 19–26. ACM, New York (2008)Google Scholar
  13. Harpale, A.S., Yang, Y.: Personalized active learning for collaborative filtering. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 91–98. ACM, New York (2008)Google Scholar
  14. Huang, Z.: Selectively acquiring ratings for product recommendation. In: Proceedings of the Ninth International Conference on Electronic Commerce (ICEC ’07), pp. 379–388. ACM, New York (2007)Google Scholar
  15. Jin, R., Si, L.: A bayesian approach toward active learning for collaborative filtering. In: Proceedings of the 20th Conference on Uncertainty in Artificial Intelligence (UAI ’04), pp. 278–285. AUAI Press, Arlington (2004)Google Scholar
  16. Karimi, R.: Active learning for recommender systems. KI-Künstliche Intelligenz, 1–4 (2014)Google Scholar
  17. Karimi, R., Freudenthaler, C., Nanopoulos, A., Schmidt-Thieme, L.: Active learning for aspect model in recommender systems. In: CIDM, Paris pp. 162–167 (2011)Google Scholar
  18. Karimi, R., Freudenthaler, C., Nanopoulos, A., Schmidt-Thieme, L.: Non-myopic active learning for recommender systems based on matrix factorization. In: IRI, Las Vegas, pp. 299–303 (2011)Google Scholar
  19. Karimi, R., Freudenthaler, C., Nanopoulos, A., Schmidt-Thieme, L.: Towards optimal active learning for matrix factorization in recommender systems. In: ICTAI, Florida, pp. 1069–1076 (2011)Google Scholar
  20. Karimi, R., Freudenthaler, C., Nanopoulos, A., Schmidt-Thiemee, L.: Exploiting the characteristics of matrix factorization for active learning in recommender systems. In: RecSys, Dublin, pp. 317–320 (2012)Google Scholar
  21. Karimi, R., Nanopoulos, A., Schmidt-Thieme, L.: Improved questionnaire trees for active learning in recommender systems. In: Proceedings of the 16th LWA Workshops: KDML, IR and FGWM, pp. 34–44. Aachen, Germany (2014)Google Scholar
  22. Karimi, R., Wistuba, M., Nanopoulos, A., Schmidt-Thieme, L.: Factorized decision trees for active learning in recommender systems. In: 2013 IEEE 25th International Conference on Tools with Artificial Intelligence (ICTAI), IEEE, Washington DC, pp. 404–411 (2013)Google Scholar
  23. Kohrs, A., Mérialdo, B.: Improving collaborative filtering for new-users by smart object selection. In: ICME 2001, International Conference on Media Futures, 8–9 May 2001, Florence (2001)Google Scholar
  24. Konstan, J.A., Miller, B.N., Maltz, D., Herlocker, J.L., Gordon, L.R., Riedl, J.: GroupLens: applying collaborative filtering to usenet news. Commun. ACM 40(3), 77–87 (1997)CrossRefGoogle Scholar
  25. Koren, Y.: How useful is a lower rmse? http://www.netflixprize.com/community/viewtopic.php?id=828/ (2007). Accessed: 15 April 2013
  26. Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’08), pp. 426–434. ACM, New York (2008)Google Scholar
  27. Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42, 30–37 (2009)CrossRefGoogle Scholar
  28. Lee, J., Jang, M., Lee, D., Hwang, W.S., Hong, J., Kim, S.W.: Alleviating the sparsity in collaborative filtering using crowdsourcing. In: Workshop on Crowdsourcing and Human Computation for Recommender Systems (CrowdRec), p. 5 (2013)Google Scholar
  29. Park, S.T., Chu, W.: Pairwise preference regression for cold-start recommendation. In: Proceedings of the Third ACM Conference on Recommender Systems (RecSys ’09), pp. 21–28. ACM, New York (2009)Google Scholar
  30. Pilászy, I., Tikk, D.: Recommending new movies: Even a few ratings are more valuable than metadata. In: Proceedings of the Third ACM Conference on Recommender Systems (RecSys ’09), pp. 93–100. ACM, New York (2009)Google Scholar
  31. Rashid, A.M., Albert, I., Cosley, D., Lam, S.K., Mcnee, S.M., Konstan, J.A., Riedl, J.: Getting to know you: Learning new user preferences in recommender systems. In: Proceedings of the International Conference on Intelligent User Interfaces, pp. 127–134. ACM Press, New York (2002)Google Scholar
  32. Rashid, A.M., Karypis, G., Riedl, J.: Learning Preferences of New Users in Recommender Systems: An Information Theoretic Approach, vol. 10, pp. 99–100. ACM, New York (2008)Google Scholar
  33. Rendle, S., Schmidt-Thieme, L.: Online-updating regularized kernel matrix factorization models for large-scale recommender systems. In: Proceedings of the 2008 ACM Conference on Recommender Systems (RecSys ’08), pp. 251–258. ACM, New York (2008)Google Scholar
  34. Rish, I., Tesauro, G.: Active collaborative prediction with maximum margin matrix factorization. In: ISAIM (2008)Google Scholar
  35. Rubens, N., Sugiyama, M.: Influence-based collaborative active learning. In: Proceedings of the 2007 ACM Conference on Recommender Systems (RecSys ’07), pp. 145–148. ACM, New York (2007)Google Scholar
  36. Safoury, L., Salah, A.: Exploiting user demographic attributes for solving cold-start problem in recommender system. Lect. Notes Softw. Eng. 1(3), 303–307 (2013)CrossRefGoogle Scholar
  37. Sutherland, D.J., Póczos, B., Schneider, J.: Active learning and search on low-rank matrices. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’13), pp. 212–220. ACM, New York (2013)Google Scholar
  38. Tong, S., Koller, D.: Active learning for structure in bayesian networks. In: Proceedings of the 17th International Joint Conference on Artificial Intelligence (IJCAI’01), vol. 2, pp. 863–869. Morgan Kaufmann Publishers Inc., San Francisco (2001)Google Scholar
  39. Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learn. Res. 2, 45–66 (2002)zbMATHGoogle Scholar
  40. Yang, B., Sun, J.T., Wang, T., Chen, Z.: Effective multi-label active learning for text classification. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’09), pp. 917–926. ACM, New York (2009)Google Scholar
  41. Zhang, L., Meng, X., Chen, J., Xiong, S.C., Duan, K.: Alleviating cold-start problem by using implicit feedback. iN: ADMA, Springer. Lecture Notes in Computer Science vol. 5678, pp. 763–771 (2009)Google Scholar
  42. Zhou, K., Yang, S.H., Zha, H.: Functional matrix factorizations for cold-start recommendation. In: 34th international ACM SIGIR conference on Research and development in Information Retrieval, (SIGIR ’11), pp 315–324. ACM, New York (2011)Google Scholar
  43. Zigoris, P.: Bayesian adaptive user profiling with explicit & implicit feedback. In. In Conference on Information and Knowledge Mangement, p. 397. ACM Press, New York (2006)Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  • Rasoul Karimi
    • 1
    Email author
  • Alexandros Nanopoulos
    • 2
  • Lars Schmidt-Thieme
    • 1
  1. 1.Information Systems and Machine Learning Lab Marienburger Platz 22University of HildesheimHildesheimGermany
  2. 2.Department of Business Informatics., Schanz 49University of Eichstatt-IngolstadtIngolstadtGermany

Personalised recommendations