Conditional preference nets for user and item cold start problems in music recommendation

A great amount of data is usually needed for a recommender system to learn the associations between users and items. However, in practical applications, new users and new items emerge everyday, and the system has to react to them promptly. The ability to recommend proper items to new users affects the users' first impression and accordingly the retention rate, whereas recommending new items to proper users contributes to the freshness of the recommendation. In this paper, we propose a deep learning model called the conditional preference nets (CPN) to deal with both new users and items under the same model framework. CPN employs an introductory user survey to learn about new users, and content features automatically extracted from items for the item side. Through a new idea called the preference vectors and an existing content embedding technique, the same model can capitalize the observed associations between known (i.e. old) users and items, thereby benefiting from the cumulative knowledge of user behavior gained over time. We validate the superiority of CPN over prior arts using the Million Song Dataset. We also demonstrate how CPN allows a user to pick either genres, artists, or the combination of them in the introductory survey.

[1]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[2]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[3]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[4]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[5]  Yiming Yang,et al.  Personalized active learning for collaborative filtering , 2008, SIGIR '08.

[6]  Lars Schmidt-Thieme,et al.  Factorizing personalized Markov chains for next-basket recommendation , 2010, WWW '10.

[7]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[8]  Yi-Hsuan Yang,et al.  Addressing Cold Start for Next-song Recommendation , 2016, RecSys.

[9]  David M. Pennock,et al.  Categories and Subject Descriptors , 2001 .

[10]  Raymond J. Mooney,et al.  Content-boosted collaborative filtering for improved recommendations , 2002, AAAI/IAAI.

[11]  Yi-Hsuan Yang,et al.  Event Localization in Music Auto-tagging , 2016, ACM Multimedia.

[12]  Benjamin Schrauwen,et al.  Deep content-based music recommendation , 2013, NIPS.

[13]  Roberto Turrin,et al.  Performance of recommender algorithms on top-n recommendation tasks , 2010, RecSys '10.

[14]  Ye Wang,et al.  Improving Content-based and Hybrid Music Recommendation using Deep Learning , 2014, ACM Multimedia.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Mu Zhu,et al.  Content-boosted matrix factorization for recommender systems: experiments with recipe recommendation , 2011, RecSys '11.

[17]  Joseph A. Konstan,et al.  Evaluating recommender behavior for new users , 2014, RecSys '14.

[18]  John Riedl,et al.  Learning preferences of new users in recommender systems: an information theoretic approach , 2008, SKDD.

[19]  Xiaodong He,et al.  A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems , 2015, WWW.

[20]  Denis Parra,et al.  Walk the talk: analyzing the relation between implicit and explicit feedback for preference elicitation , 2011, UMAP'11.

[21]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[22]  Alessandro Moschitti,et al.  Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks , 2015, SIGIR.

[23]  James Bennett,et al.  The Netflix Prize , 2007 .

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

[25]  Thierry Bertin-Mahieux,et al.  The million song dataset challenge , 2012, WWW.