{"type":"ScholarlyArticle","title":"Hierarchical Bayesian Matrix Factorization with Side Information","authors":[{"name":"Sunho Park","slug":"sunho-park","given":"Sunho","family":"Park","affiliation":"Department of Computer Science and Engineering"},{"name":"Yong-Deok Kim","slug":"yong-deok-kim","given":"Yong-Deok","family":"Kim","affiliation":"Department of Computer Science and Engineering"},{"name":"Seungjin Choi","slug":"seungjin-choi","given":"Seungjin","family":"Choi","affiliation":"Department of Computer Science and Engineering; Division of IT Convergence Engineering Pohang University of Science and Technology 77 Cheongam-ro , Nam-gu , Pohang 790-784 , Korea"}],"abstract":"Bayesian treatment of matrix factorization has been successfully applied to the problem of collaborative prediction,where unknown ratings are determined by the predictive distribution, inferring posterior distributions over user and item factor matrices that are used to approximate the user-item matrix as their product. In practice, however, Bayesian matrix factorization suffers from cold-start problems, where inferences are required for users or items about which a sufficient number of ratings are not gathered. In this paper we present a method for Bayesian matrix factorization with side information, to handle cold-start problems. To this end, we place Gaussian-Wishart priors on mean vectors and precision matrices of Gaussianuser and item factor matrices, such that mean of each prior distribution is regressed on corresponding side information. We develop variational inference algorithms to approximately compute posterior distributions over user and item factor matrices.In addition, we provide Bayesian Cramér-Rao Bound for our model, showing that the hierarchical Bayesian matrix factorization with side information improves the reconstruction over the standard Bayesian matrix factorization where the side information is not used. Experiments on MovieLens data demonstrate the useful behavior of our model in the case of cold-start problems.","doi":null,"url":"https://ijcai.org/proceedings/2013/237","pdf":"https://ijcai.org/proceedings/2013/0237.pdf","markdown":"https://ijcai.org/proceedings/2013/237.md","bibtex":"https://ijcai.org/proceedings/2013/bibtex/237","volume":{"slug":"2013","title":"Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2013","url":"https://ijcai.org/proceedings/2013/","year":2013,"location":"Beijing, China","dates":"3–9 August 2013","editors":"Francesca Rossi","isbn":"978-1-57735-633-2","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":237,"pages":{"first":1593,"last":1598},"keywords":[],"videos":[],"references":[{"position":1,"raw":"[Agarwal and Chen, 2009] D. Agarwal and B.-C. Chen. Regression-based latent factor models. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Paris, France, 2009.","title":"Regression-based latent factor models","authors":"D, B.-C Chen","year":"2009","venue":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Kim and Choi, 2013] Y.-D. Kim and S. Choi. Variational Bayesian view of weighted trace norm regularization for matrix factorization. IEEE Signal Processing Letters, 20(3):261-264, 2013.","title":"Variational Bayesian view of weighted trace norm regularization for matrix factorization","authors":"Y.-D Kim, S Choi","year":"2013","venue":"IEEE Signal Processing Letters","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Koren et al., 2009] Y. Koren, R. Bell, and C. Volinsky. Ma- trix factorization techniques for recommender systems. IEEE Computer, 42(8):30-37, 2009.","title":"Matrix factorization techniques for recommender systems","authors":"Y Koren, R Bell, C Volinsky","year":"2009","venue":"IEEE Computer","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Lim and Teh, 2007] Y. J. Lim and Y. W. Teh. Variational Bayesian approach to movie rating prediction. In Proceed- ings of KDD Cup and Workshop, San Jose, CA, 2007.","title":"Variational Bayesian approach to movie rating prediction","authors":"Y J Lim, Y W Teh","year":"2007","venue":"Proceedings of KDD Cup and Workshop","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Proteous et al., 2010] I. Proteous, A. Asuncion, and M. Welling. Bayesian matrix factorization with side in- formation and Dirichlet process mixtures. In Proceedings of the AAAI National Conference on Artificial Intelligence (AAAI), Atlanta, Georgia, USA, 2010.","title":"Bayesian matrix factorization with side information and Dirichlet process mixtures","authors":"Proteous","year":"2010","venue":"Proceedings of the AAAI National Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Raiko et al., 2007] T. Raiko, A. Ilin, and J. Karhunen. Prin- cipal component analysis for large scale problems with lots of missing values. In Proceedings of the European Confer- ence on Machine Learning (ECML), pages 691-698, War- saw, Poland, 2007.","title":"Principal component analysis for large scale problems with lots of missing values","authors":"T Raiko, A Ilin, J Karhunen","year":"2007","venue":"Proceedings of the European Conference on Machine Learning (ECML)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Rennie and Srebro, 2005] J. D. M. Rennie and N. Srebro. Fast maximum margin matrix factorization for collabora- tive prediction. In Proceedings of the International Con- ference on Machine Learning (ICML), Bonn, Germany, 2005.","title":"Fast maximum margin matrix factorization for collaborative prediction","authors":"J D M Rennie, N Srebro","year":"2005","venue":"Proceedings of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Salakhutdinov and Mnih, 2008a] R. Salakhutdinov and A. Mnih. Bayesian probablistic matrix factorization using MCMC. In Proceedings of the International Conference on Machine Learning (ICML), Helsinki, Finland, 2008.","title":"Bayesian probablistic matrix factorization using MCMC","authors":"Mnih Salakhutdinov, R Salakhutdinov, A Mnih","year":"2008","venue":"Proceedings of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Salakhutdinov and Mnih, 2008b] R. Salakhutdinov and A. Mnih. Probablistic matrix factorization. In Advances in Neural Information Processing Systems (NIPS), volume 20. MIT Press, 2008.","title":"Probablistic matrix factorization","authors":"R Salakhutdinov, A Mnih","year":"2008","venue":"Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Singh and Gordon, 2008] A. P. Singh and G. J. Gordon. Re- lational learning via collective matrix factorization. In Proceedings of the ACM SIGKDD Conference on Knowl- edge Discovery and Data Mining (KDD), Las Vegas, Nevada, 2008.","title":"Relational learning via collective matrix factorization","authors":"A P Singh, G J Gordon","year":"2008","venue":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Singh and Gordon, 2010] A. P. Singh and G. J. Gordon. A Bayesian matrix factorization model for relational data. In Proceedings of the Annual Conference on Uncertainty in Artificial Intelligence (UAI), Catalina Island, CA, 2010.","title":"A Bayesian matrix factorization model for relational data","authors":"A P Singh, G J Gordon","year":"2010","venue":"Proceedings of the Annual Conference on Uncertainty in Artificial Intelligence (UAI)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Takács et al., 2009] G. Takács, I. Pilászy, B. Németh, and D. Tikk. Scalable collaborative filtering approaches for large recommender systems. Journal of Machine Learning Research, 10:623-656, 2009.","title":"Scalable collaborative filtering approaches for large recommender systems","authors":"G Takács, I Pilászy, B Németh, D Tikk","year":"2009","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Tichavsky et al., 1998] P. Tichavsky, C. H. Muravchik, and A. Nehorai. Posterior Cramér-Rao bounds for discrete- time nonlinear filtering. IEEE Transactions on Signal Pro- cessing, 46(5):1386-1395, 1998.","title":"Posterior Cramér-Rao bounds for discretetime nonlinear filtering","authors":"P Tichavsky, C H Muravchik, A Nehorai","year":"1998","venue":"IEEE Transactions on Signal Processing","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Yoo and Choi, 2011] J. Yoo and S. Choi. Bayesian matrix co-factorization: Variational algorithm and Cramér-Rao bound. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowl- edge Discovery in Databases (ECML-PKDD), Athens, Greece, 2011.","title":"Bayesian matrix co-factorization: Variational algorithm and Cramér-Rao bound","authors":"Choi Yoo, ] J Yoo, S Choi","year":"2011","venue":"Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Yoo and Choi, 2012] J. Yoo and S. Choi. Hierarchical varia- tional Bayesian matrix co-factorization. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Japan, 2012.","title":"Hierarchical variational Bayesian matrix co-factorization","authors":"Choi Yoo, ] J Yoo, S Choi","year":"2012","venue":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}