Cross-Domain Recommender Systems

Most recommender systems work on single domains, i.e., they recommend items related to the same domain where users have expressed ratings. However, the integration of different domains into one recommender system could allow users to span over different types of items. For instance, users that have watched live TV programs could like to be recommended with on-demand movies, music, mobile applications, friends to connect to, etc. This paper focuses on cross-domain collaborative recommender systems, whose aim is to suggest items related to multiple domains. We first formalize the cross-domain problem in order to provide a common framework for the classification and the evaluation of state-of-the-art algorithms. We later define a new class of cross-domain algorithms based on neighborhood collaborative filtering, either item-based or user-based. The main idea is to first model the classical similarity relationships (e.g., Pearson, cosine) as a direct graph and to later explore all possible paths connecting users or items in order to find new, cross-domain, relationships. The algorithms have been tested on three cross-domain scenarios artificially reproduced by partitioning the Netflix dataset.

[1]  Qiang Yang,et al.  Active Transfer Learning for Cross-System Recommendation , 2013, AAAI.

[2]  Qiang Yang,et al.  Can Movies and Books Collaborate? Cross-Domain Collaborative Filtering for Sparsity Reduction , 2009, IJCAI.

[3]  Alexander J. Smola,et al.  Multiple domain user personalization , 2011, KDD.

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

[5]  Shaghayegh Sahebi,et al.  Cross-Domain Collaborative Recommendation in a Cold-Start Context: The Impact of User Profile Size on the Quality of Recommendation , 2013, UMAP.

[6]  Martha Larson,et al.  Tags as bridges between domains: improving recommendation with tag-induced cross-domain collaborative filtering , 2011, UMAP'11.

[7]  Tsvi Kuflik,et al.  Cross social networks interests predictions based ongraph features , 2013, RecSys.

[8]  Martin Szomszor,et al.  Semantic Modelling of User Interests Based on Cross-Folksonomy Analysis , 2008, SEMWEB.

[9]  Martin Szomszor,et al.  Correlating user profiles from multiple folksonomies , 2008, Hypertext.

[10]  Iván Cantador,et al.  Ontology-Based Identification of Music for Places , 2013, ENTER.

[11]  Chris H. Q. Ding,et al.  Orthogonal nonnegative matrix t-factorizations for clustering , 2006, KDD '06.

[12]  David Dupplaw,et al.  The semantic logger: supporting service building from personal context , 2006, CARPE '06.

[13]  Lior Rokach,et al.  Recommender Systems Handbook , 2010 .

[14]  Yasuhiro Fujiwara,et al.  Recommendations Over Domain Specific User Graphs , 2010, ECAI.

[15]  Guy Shani,et al.  TALMUD: transfer learning for multiple domains , 2012, CIKM.

[16]  Tiffany Ya Tang,et al.  If You Like the Devil Wears Prada the Book, Will You also Enjoy the Devil Wears Prada the Movie? A Study of Cross-Domain Recommendations , 2008, New Generation Computing.

[17]  Geert-Jan Houben,et al.  Cross-system user modeling and personalization on the Social Web , 2013, User Modeling and User-Adapted Interaction.

[18]  Tsvi Kuflik,et al.  Identifying Inter-Domain Similarities Through Content-Based Analysis of Hierarchical Web-Directories , 2006, ECAI.

[19]  Qi Gao,et al.  Analyzing Cross-System User Modeling on the Social Web , 2011, ICWE.

[20]  Guandong Xu,et al.  Personalized recommendation via cross-domain triadic factorization , 2013, WWW.

[21]  Francesco Ricci,et al.  Cold-Start Management with Cross-Domain Collaborative Filtering and Tags , 2013, EC-Web.

[22]  Gustavo González,et al.  A Multi-agent Smart User Model for Cross-domain Recommender Systems , 2005 .

[23]  Qiang Yang,et al.  Transfer learning for collaborative filtering via a rating-matrix generative model , 2009, ICML '09.

[24]  Sree Hari Krishnan Parthasarathi,et al.  Exploiting innocuous activity for correlating users across sites , 2013, WWW.

[25]  Federica Cena,et al.  User identification for cross-system personalisation , 2009, Inf. Sci..

[26]  Fei Wang,et al.  Recommendation on Item Graphs , 2006, Sixth International Conference on Data Mining (ICDM'06).

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

[28]  Iván Cantador,et al.  Cross-domain recommender systems : A survey of the State of the Art , 2012 .

[29]  Tsvi Kuflik,et al.  Entertainment Personalization Mechanism Through Cross-Domain User Modeling , 2005, INTETAIN.

[30]  Mustafa Azak,et al.  CROSSING: A FRAMEWORK TO DEVELOP KNOWLEDGE-BASED RECOMMENDERS IN CROSS DOMAINS , 2010 .

[31]  Bin Li,et al.  Cross-Domain Collaborative Filtering: A Brief Survey , 2011, 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence.

[32]  Guy Shani,et al.  Evaluating Recommendation Systems , 2011, Recommender Systems Handbook.

[33]  Anupam Joshi,et al.  @i seek 'fb.me': identifying users across multiple online social networks , 2013, WWW.

[34]  Bin Cao,et al.  Multi-Domain Collaborative Filtering , 2010, UAI.

[35]  Brendan Kitts,et al.  Cross-sell: a fast promotion-tunable customer-item recommendation method based on conditionally independent probabilities , 2000, KDD '00.

[36]  Qiang Yang,et al.  Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Transfer Learning to Predict Missing Ratings via Heterogeneous User Feedbacks , 2022 .

[37]  Lior Rokach,et al.  Facebook single and cross domain data for recommendation systems , 2013, User Modeling and User-Adapted Interaction.

[38]  Ronald Chung,et al.  Integrated personal recommender systems , 2007, ICEC.

[39]  Xi Zhang,et al.  TopRec: domain-specific recommendation through community topic mining in social network , 2013, WWW '13.

[40]  Xindong Wu,et al.  Cross-Domain Collaborative Filtering over Time , 2011, IJCAI.

[41]  Tsvi Kuflik,et al.  Cross-Domain Mediation in Collaborative Filtering , 2007, User Modeling.

[42]  Zheng Chen,et al.  Collaborative Users' Brand Preference Mining across Multiple Domains from Implicit Feedbacks , 2011, AAAI.

[43]  Chi-Hoon Lee,et al.  Web personalization expert with combining collaborative filtering and association rule mining technique , 2001, Expert Syst. Appl..

[44]  Antonis Loizou,et al.  How to recommend music to film buffs: enabling the provision of recommendations from multiple domains , 2009 .

[45]  Qiang Yang,et al.  Transfer Learning for Collective Link Prediction in Multiple Heterogenous Domains , 2010, ICML.

[46]  Shlomo Berkovsky,et al.  Evaluating Recommender Systems for Supportive Technologies , 2013 .

[47]  Qiang Yang,et al.  Transfer Learning in Collaborative Filtering for Sparsity Reduction , 2010, AAAI.

[48]  Alejandro Bellogín,et al.  Relating Personality Types with User Preferences in Multiple Entertainment Domains , 2013, UMAP Workshops.

[49]  Iván Cantador,et al.  An Emotion Dimensional Model Based on Social Tags: Crossing Folksonomies and Enhancing Recommendations , 2013, EC-Web.

[50]  Tsvi Kuflik,et al.  Domain ranking for cross domain collaborative filtering , 2012, UMAP.

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

[52]  Pablo A. Haya,et al.  User Modeling and Adaptation for Daily Routines , 2013, Human–Computer Interaction Series.

[53]  Hyung Joon Kook,et al.  Profiling Multiple Domains of User Interests and Using Them for Personalized Web Support , 2005, ICIC.

[54]  Qiang Yang,et al.  Transfer learning in heterogeneous collaborative filtering domains , 2013, Artif. Intell..

[55]  Victor Lavrenko,et al.  Predicting social-tags for cold start book recommendations , 2009, RecSys '09.

[56]  Tsvi Kuflik,et al.  Mediation of user models for enhanced personalization in recommender systems , 2007, User Modeling and User-Adapted Interaction.

[57]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[58]  Francesco Ricci,et al.  Location-aware music recommendation , 2013, International Journal of Multimedia Information Retrieval.

[59]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[60]  Avare Stewart,et al.  Cross-tagging for personalized open social networking , 2009, HT '09.

[61]  Federica Cena,et al.  User model interoperability: a survey , 2011, User Modeling and User-Adapted Interaction.

[62]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[63]  J. Riedl,et al.  Recommender Systems for E-Commerce : Challenges and Opportunities , 1999 .

[64]  Iván Cantador,et al.  A generic semantic-based framework for cross-domain recommendation , 2011, HetRec '11.

[65]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[66]  Hui Xiong,et al.  Cross-Domain Learning from Multiple Sources: A Consensus Regularization Perspective , 2010, IEEE Transactions on Knowledge and Data Engineering.

[67]  Hao Luo,et al.  Cross-Domain Recommendation via Cluster-Level Latent Factor Model , 2013, ECML/PKDD.

[68]  John Riedl,et al.  Application of Dimensionality Reduction in Recommender System - A Case Study , 2000 .

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

[70]  Tsvi Kuflik,et al.  Distributed collaborative filtering with domain specialization , 2007, RecSys '07.

[71]  Qiang Yang,et al.  Transfer Learning via Dimensionality Reduction , 2008, AAAI.