An Improved Matrix Approximation for Recommender Systems Based on Context-Information and Transfer Learning

As we all known, transfer learning is an effective way to alleviate the sparsity problem in recommender systems by transferring the shared knowledge cross multiple related domains. However, additional related domain is not always available, and auxiliary data may be noisy and this leads to negative transfer. In this paper, we suppose that different parts of one domain also have the shared knowledge and put forward a novel in-domain collaborative filtering framework, which utilizes contextual information to divide an original user-item interaction matrix into some smaller sub-matrices and regards the selected sub-matrices as “multiple domains” to establish transfer learning. The proposed framework no longer needs additional domain information and has a better adaptive ability. Also, considering more actual situation that users may have multiple personalities and items may have diverse attributes, we resort to Rating-Matrix Generative Model (RMGM) to generate the shared cluster-level rating pattern. Experiments on dataset Douban with three different categories demonstrate that the proposed framework can improve the prediction accuracy as well as the top-N recommendation performance.

[1]  Hinrich Schütze,et al.  Introduction to information retrieval , 2008 .

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

[3]  Zhen Lin,et al.  Context-Aware Collaborative Topic Regression with Social Matrix Factorization for Recommender Systems , 2014, AAAI.

[4]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[5]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[6]  Luo Si,et al.  Flexible Mixture Model for Collaborative Filtering , 2003, ICML.

[7]  Kaisheng Yao,et al.  Robust Transfer Learning for Cross-domain Collaborative Filtering Using Multiple Rating Patterns Approximation , 2018, WSDM.

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

[9]  Zhong Ming,et al.  Interaction-Rich Transfer Learning for Collaborative Filtering with Heterogeneous User Feedback , 2014, IEEE Intelligent Systems.

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

[11]  Qiang Yang,et al.  Contextual Collaborative Filtering via Hierarchical Matrix Factorization , 2012, SDM.

[12]  David Heckerman,et al.  Empirical Analysis of Predictive Algorithms for Collaborative Filtering , 1998, UAI.

[13]  Xu Yu,et al.  SVMs Classification Based Two-side Cross Domain Collaborative Filtering by inferring intrinsic user and item features , 2018, Knowl. Based Syst..

[14]  Zhong Ming,et al.  Mixed factorization for collaborative recommendation with heterogeneous explicit feedbacks , 2016, Inf. Sci..

[15]  Hsinchun Chen,et al.  A Comparison of Collaborative-Filtering Recommendation Algorithms for E-commerce , 2007, IEEE Intelligent Systems.

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

[17]  Qiang Yang,et al.  A unified framework of active transfer learning for cross-system recommendation , 2017, Artif. Intell..

[18]  David Maxwell Chickering,et al.  Dependency Networks for Inference, Collaborative Filtering, and Data Visualization , 2000, J. Mach. Learn. Res..

[19]  Xiang Li,et al.  Improving matrix approximation for recommendation via a clustering-based reconstructive method , 2016, Neurocomputing.

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

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

[22]  Lior Rokach,et al.  Utilizing transfer learning for in-domain collaborative filtering , 2016, Knowl. Based Syst..

[23]  Karl Aberer,et al.  SoCo: a social network aided context-aware recommender system , 2013, WWW.

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

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

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

[27]  Deren Chen,et al.  Context-Aware Trust Aided Recommendation via Ontology and Gaussian Mixture Model in Big Data Environment , 2014, 2014 International Conference on Service Sciences.

[28]  Feng Jiang,et al.  A cross-domain collaborative filtering algorithm with expanding user and item features via the latent factor space of auxiliary domains , 2019, Pattern Recognit..

[29]  Jun Li,et al.  Towards Context-aware Social Recommendation via Individual Trust , 2017, Knowl. Based Syst..

[30]  Sarik Ghazarian,et al.  Enhancing memory-based collaborative filtering for group recommender systems , 2015, Expert Syst. Appl..

[31]  Chen Ding,et al.  Progress in context-aware recommender systems - An overview , 2019, Comput. Sci. Rev..

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

[33]  Qian Zhang,et al.  A cross-domain recommender system with consistent information transfer , 2017, Decis. Support Syst..

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