Gated Probabilistic Matrix Factorization: Learning Users' Attention from Missing Values

Recommender systems rely on techniques of predicting the ratings that users would give to yet unconsumed items. Probabilistic matrix factorization (PMF) is a standard technique for such prediction and makes a prediction on the basis of an underlying probabilistic generative model of the behavior of users. We investigate a new model of users' consumption and rating, where a user tends to consume an item that emphasizes those features that the user seeks to enjoy, and the ratings of the users are more strongly affected by those features than others. We incorporate this new user model into PMF and show that the resulting method, Gated PMF (GPMF), improves the predictive accuracy by several percent on standard datasets. GPMF is widely applicable, as it is trained only with the ratings given by users and does not rely on any auxiliary data.

[1]  Eileen A. Hogan.  The Attention Economy: Understanding the New Currency of Business , 2001 .

[2]  Daniel Gooch,et al.  Communications of the ACM , 2011, XRDS.

[3]  P. Cavanagh.  Visual cognition , 2011, Vision Research.

[4]  Michael R. Lyu,et al.  SoRec: social recommendation using probabilistic matrix factorization , 2008, CIKM '08.

[5]  Guillaume Bouchard,et al.  Robust Bayesian Matrix Factorisation , 2011, AISTATS.

[6]  Prateek Jain,et al.  Low-rank matrix completion using alternating minimization , 2012, STOC '13.

[7]  Thomas Hofmann,et al.  Latent semantic models for collaborative filtering , 2004, TOIS.

[8]  Zoubin Ghahramani,et al.  Probabilistic Matrix Factorization with Non-random Missing Data , 2014, ICML.

[9]  Honglak Lee,et al.  Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines , 2013, ICML.

[10]  Toon De Pessemier,et al.  MovieTweetings: a movie rating dataset collected from twitter , 2013, RecSys 2013.

[11]  Peter Kulchyski.  and , 2015 .

[12]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[13]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[14]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[15]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[16]  Ronald A. Rensink.  The Dynamic Representation of Scenes , 2000 .

[17]  Jan P.L. Schoormans,et al.  The effect of new package design on product attention, categorization and evaluation , 1997 .

[18]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[19]  M. Corbetta,et al.  Control of goal-directed and stimulus-driven attention in the brain , 2002, Nature Reviews Neuroscience.

[20]  Shinichi Nakajima,et al.  Implicit Regularization in Variational Bayesian Matrix Factorization , 2010, ICML.

[21]  Martin Ester,et al.  A Transitivity Aware Matrix Factorization Model for Recommendation in Social Networks , 2011, IJCAI.

[22]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[23]  Richard S. Zemel,et al.  Collaborative prediction and ranking with non-random missing data , 2009, RecSys '09.

[24]  Steffen Rendle,et al.  Learning recommender systems with adaptive regularization , 2012, WSDM '12.

[25]  Qiang Yang,et al.  Transfer Learning in Collaborative Filtering with Uncertain Ratings , 2012, AAAI.

[26]  Tommi S. Jaakkola,et al.  Maximum-Margin Matrix Factorization , 2004, NIPS.

[27]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[28]  Jure Leskovec,et al.  From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews , 2013, WWW.

[29]  Ruslan Salakhutdinov,et al.  Bayesian probabilistic matrix factorization using Markov chain Monte Carlo , 2008, ICML '08.