ABSTRACT
This paper studies result diversification in collaborative filtering. We argue that the diversification level in a recommendation list should be adapted to the target users' individual situations and needs. Different users may have different ranges of interests -- the preference of a highly focused user might include only few topics, whereas that of the user with broad interests may encompass a wide range of topics. Thus, the recommended items should be diversified according to the interest range of the target user. Such an adaptation is also required due to the fact that the uncertainty of the estimated user preference model may vary significantly between users. To reduce the risk of the recommendation, we should take the difference of the uncertainty into account as well.
In this paper, we study the adaptive diversification problem theoretically. We start with commonly used latent factor models and reformulate them using the mean-variance analysis from the portfolio theory in text retrieval. The resulting Latent Factor Portfolio (LFP) model captures the user's interest range and the uncertainty of the user preference by employing the variance of the learned user latent factors. It is shown that the correlations between items (and thus the item diversity) can be obtained by using the correlations between latent factors (topical diversity), which in return significantly reduce the computation load. Our mathematical derivation also reveals that diversification is necessary, not only for risk-averse system behavior (non-adpative), but also for the target users' individual situations (adaptive), which are represented by the distribution and the variance of the latent user factors. Our experiments confirm the theoretical insights and show that LFP succeeds in improving latent factor models by adaptively introducing recommendation diversity to fit the individual user's needs.
- G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Kowledge and Data Engineering, 17(6):734--749, 2005. Google ScholarDigital Library
- D. Agarwal and B.-C. Chen. Regression-based latent factor models. KDD '09, pages 19--28, 2009. Google ScholarDigital Library
- L. Azzopardi. The economics in interactive information retrieval. SIGIR '11, pages 15--24, 2011. Google ScholarDigital Library
- R. Bambini, P. Cremonesi, and R. Turrin. Recommender Systems Handbook, chapter Recommender Systems for a IPTV Service Provider: A Real Production Environment. Springer, 2010.Google Scholar
- D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. J. Mach. Learn. Res., 2003. Google ScholarDigital Library
- J. Carbonell and J. Goldstein. The use of MMR diversity-based reranking for reordering documents and producing summaries. SIGIR '98, pages 335--336, 1998. Google ScholarDigital Library
- H. Chen and D. R. Karger. Less is more: probabilistic models for retrieving fewer relevant documents. SIGIR '06, 2006. Google ScholarDigital Library
- C. L. Clarke, M. Kolla, G. V. Cormack, O. Vechtomova, A. Ashkan, S. Büttcher, and I. MacKinnon. Novelty and diversity in information retrieval evaluation. SIGIR '08, pages 659--666, 2008. Google ScholarDigital Library
- P. Cremonesi, Y. Koren, and R. Turrin. Performance of recommender algorithms on top-N recommendation tasks. RecSys '10, pages 39--46, 2010. Google ScholarDigital Library
- S. Guo and S. Sanner. Probabilistic latent maximal marginal relevance. SIGIR '10, pages 833--834, 2010. Google ScholarDigital Library
- A. S. Harpale and Y. Yang. Personalized active learning for collaborative filtering. SIGIR '08, pages 91--98, 2008. Google ScholarDigital Library
- J. L. Herlocker, J. A. Konstan, A. Borchers, and J. Riedl. An algorithmic framework for performing collaborative filtering. SIGIR '99, pages 230--237, 1999. Google ScholarDigital Library
- N. Hurley and M. Zhang. Novelty and diversity in top-N recommendation -- analysis and evaluation. ACM Trans. Internet Technol., 10:14:1--14:30, March 2011. Google ScholarDigital Library
- T. Jambor, J. Wang, and N. Lathia. Using control theory for stable and efficient recommender systems. WWW '12, pages 11--20, 2012. Google ScholarDigital Library
- K. J\"arvelin and J. Kek\"al\"ainen. Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst., 20:422--446, October 2002. Google ScholarDigital Library
- Y. Koren. Factorization meets the neighborhood: a multifaceted collaborative filtering model. KDD '08, pages 426--434, 2008. Google ScholarDigital Library
- Y. Koren, R. Bell, and C. Volinsky. Matrix factorization techniques for recommender systems. Computer, 42:30--37, August 2009. Google ScholarDigital Library
- M. Kurucz, A. A. Benczúr, and K. Csalogány. Methods for large scale svd with missing values. In Proceedings of KDD Cup and Workshop, 2007.Google Scholar
- N. Lathia, S. Hailes, L. Capra, and X. Amatriain. Temporal diversity in recommender systems. SIGIR '10, pages 210--217, 2010. Google ScholarDigital Library
- F. Radlinski and S. Dumais. Improving personalized web search using result diversification. SIGIR '06, pages 691--692, 2006. Google ScholarDigital Library
- P. Resnick. Personalized filters yes; bubbles no. http://presnick.livejournal.com/21239.html, July 2011.Google Scholar
- R. Salakhutdinov and A. Mnih. Probabilistic matrix factorization. NIPS '08, 2008.Google Scholar
- R. L. Santos, C. Macdonald, and I. Ounis. Selectively diversifying web search results. CIKM '10, pages 1179--1188, 2010. Google ScholarDigital Library
- R. L. Santos, C. Macdonald, and I. Ounis. Intent-aware search result diversification. SIGIR '11, pages 595--604, 2011. Google ScholarDigital Library
- B. Sarwar, G. Karypis, J. Konstan, and J. Reidl. Item-based collaborative filtering recommendation algorithms. WWW '01, pages 285--295, 2001. Google ScholarDigital Library
- U. Shardanand and P. Maes. Social information filtering: algorithms for automating 'word of mouth'. CHI '95, pages 210--217, 1995. Google ScholarDigital Library
- M. Sloan and J. Wang. Dynamical information retrieval modelling: a portfolio-armed bandit machine approach. WWW '12, pages 603--604, 2012. Google ScholarDigital Library
- J. Teevan, S. T. Dumais, and E. Horvitz. Potential for personalization. ACM Trans. Comput.-Hum. Interact., 17(1):4:1--4:31, Apr. 2010. Google ScholarDigital Library
- S. Vargas and P. Castells. Rank and relevance in novelty and diversity metrics for recommender systems. RecSys '11, pages 109--116, 2011. Google ScholarDigital Library
- J. Wang. Mean-variance analysis: A new document ranking theory in information retrieval. ECIR '09, pages 4--16, 2009. Google ScholarDigital Library
- J. Wang and Y. Zhang. Utilizing marginal net utility for recommendation in e-commerce. SIGIR '11, pages 1003--1012, 2011. Google ScholarDigital Library
- J. Wang and J. Zhu. Portfolio theory of information retrieval. SIGIR '09, pages 115--122, 2009. Google ScholarDigital Library
- J. Wang and J. Zhu. On statistical analysis and optimization of information retrieval effectiveness metrics. SIGIR '10, pages 226--233, 2010. Google ScholarDigital Library
- S.-H. Yang, B. Long, A. J. Smola, H. Zha, and Z. Zheng. Collaborative competitive filtering: learning recommender using context of user choice. SIGIR '11, pages 295--304, 2011. Google ScholarDigital Library
- C. X. Zhai, W. W. Cohen, and J. Lafferty. Beyond independent relevance: methods and evaluation metrics for subtopic retrieval. SIGIR '03, pages 10--17, 2003. Google ScholarDigital Library
- C.-N. Ziegler, S. M. McNee, J. A. Konstan, and G. Lausen. Improving recommendation lists through topic diversification. WWW '05, pages 22--32, 2005. Google ScholarDigital Library
Index Terms
- Adaptive diversification of recommendation results via latent factor portfolio
Recommendations
Improving recommendation lists through topic diversification
WWW '05: Proceedings of the 14th international conference on World Wide WebIn this work we present topic diversification, a novel method designed to balance and diversify personalized recommendation lists in order to reflect the user's complete spectrum of interests. Though being detrimental to average accuracy, we show that ...
Improving Latent Factor Models via Personalized Feature Projection for One Class Recommendation
CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge ManagementLatent Factor models, which transform both users and items into the same latent feature space, are one of the most successful and ubiquitous models in recommender systems. Most existing models in this paradigm define both users' and items' latent ...
A framework for diversifying recommendation lists by user interest expansion
Recommender systems have been widely used to discover users' preferences and recommend interesting items to users during this age of information overload. Researchers in the field of recommender systems have realized that the quality of a top-N ...
Comments