Wei Chen
ABSTRACT
Given the vast amount of information on the World Wide Web, recommender systems are increasingly being used to help filter irrelevant data and suggest information that would interest users. Traditional systems make recommendations based on a single domain e.g., movie or book domain. Recent work has examined the correlations in different domains and designed models that exploit user preferences on a source domain to predict user preferences on a target domain. However, these methods are based on matrix factorization and can only be applied to two-dimensional data. Transferring high dimensional data from one domain to another requires decomposing the high dimensional data to binary relations which results in information loss.
Furthermore, this decomposition creates a large number of matrices that need to be transferred and combining them in the target domain is non-trivial. Separately, researchers have looked into using social network information to improve recommendation. However, this social network information has not been explored in cross domain collaborative filtering. In this work, we propose a generalized cross domain collaborative filtering framework that integrates social network information seamlessly with cross domain data. This is achieved by utilizing tensor factorization with topic based social regularization. This framework is able to transfer high dimensional data without the need for decomposition by finding shared implicit cluster-level tensor from multiple domains. Extensive experiments conducted on real world datasets indicate that the proposed framework outperforms state-of-art algorithms for item recommendation, user recommendation and tag recommendation.
- W. Pan, N. N. Liu, E. W. Xiang, and Q. Yang, "Transfer learning to predict missing ratings via heterogeneous user feedbacks." in phIJCAI, 2011, pp. 2318--2323. Google Scholar
Digital Library
- B. Li, Q. Yang, and X. Xue, "Transfer learning for collaborative filtering via a rating-matrix generative model," in phICML, 2009, pp. 617--624. Google ScholarDigital Library
- Y. Shi, M. Larson, and A. Hanjalic, "Tags as bridges between domains: improving recommendation with tag-induced cross-domain collaborative filtering," in phUMAP, 2011, pp. 305--316. Google ScholarDigital Library
- M. Jamali and M. Ester, "A transitivity aware matrix factorization model for recommendation in social networks." in phIJCAI, 2011, pp. 2644--2649. Google ScholarDigital Library
- H. Ma, D. Zhou, C. Liu, M. R. Lyu, and I. King, "Recommender systems with social regularization," in phWSDM, 2011. Google ScholarDigital Library
- L. D. Lathauwer, B. D. Moor, and J. Vandewalle, "A multilinear singular value decomposition," phSIAM J. Matrix Anal. Appl., vol. 21, pp. 1253--1278, March 2000. Google ScholarDigital Library
- Y.-D. Kim and S. Choi, "Nonnegative tucker decomposition." in phCVPR.\hskip 1em plus 0.5em minus 0.4em\relax IEEE Computer Society, 2007, pp. 1 --8.Google Scholar
- D. D. Lee and H. S. Seung, "Algorithms for non-negative matrix factorization," in phNIPS, 2000, pp. 556--562.Google Scholar
- P. Resnick, N. Iacovou, M. Sushak, P. Bergstrom, and J. Riedl, "Grouplens: An open architecture for collaborative filtering of netnews," in phCSCWC, 1994, pp. 175--186. Google ScholarDigital Library
- M. Deshpande and G. Karypis, "Item-based top-n recommendation algorithms," phACM Transactions on Information Systems, vol. 22, pp. 143--177, 2004. Google ScholarDigital Library
- P. Symeonidis, A. Nanopoulos, and Y. Manolopoulos, "A unified framework for providing recommendations in social tagging systems based on ternary semantic analysis," phIEEE TKDE, 2010. Google ScholarDigital Library
- S. Rendle, L. Balby Marinho, A. Nanopoulos, and L. Schmidt-Thieme, "Learning optimal ranking with tensor factorization for tag recommendation," in phKDD, 2009, pp. 727--736. Google ScholarDigital Library
- C. Wei, W. Hsu, and M. L. Lee, "A unified framework for recommendations based on quaternary semantic analysis," in phSIGIR, 2011, pp. 1023--1032. Google ScholarDigital Library
- C. Liu, H.-c. Yang, J. Fan, L.-W. He, and Y.-M. Wang, "Distributed nonnegative matrix factorization for web-scale dyadic data analysis on mapreduce," ser. WWW, 2010, pp. 681--690. Google ScholarDigital Library
- G.-R. Xue, C. Lin, Q. Yang, W. Xi, H.-J. Zeng, Y. Yu, and Z. Chen, "Scalable collaborative filtering using cluster-based smoothing," in phSIGIR, 2005, pp. 114--121. Google ScholarDigital Library
- Y. Koren, "Factorization meets the neighborhood: a multifaceted collaborative filtering model," in phKDD, 2008, pp. 426--434. Google ScholarDigital Library
- J. A. Golbeck, "Computing and applying trust in web-based social networks," Ph.D. dissertation, 2005. Google ScholarDigital Library
- M. Jamali and M. Ester, "Trustwalker: a random walk model for combining trust-based and item-based recommendation," in phKDD, 2009, pp. 397--406. Google ScholarDigital Library
- Y. Shen and R. Jin, "Learning personalGoogle Scholar
- social latent factor model for social recommendation," in phKDD, 2012, pp. 1303--1311. Google ScholarDigital Library
Index Terms
- Making recommendations from multiple domains
Recommendations
User Similarity Adjustment for Improved Recommendations
MIKE 2015: Proceedings of the Third International Conference on Mining Intelligence and Knowledge Exploration - Volume 9468Recommender systems are becoming more and more attractive in both research and commercial communities due to Information overload problem and the popularity of the Internet applications. Collaborative Filtering, a popular branch of recommendation ...
Enhancing collaborative recommendation performance by combining user preference and trust-distrust propagation in social networks
Collaborative filtering (CF) is one of the most popular recommendation methods, and the co-rating-based similarity measurement is widely used in CF for predicting ratings of unfamiliar items. In addition to rating information, social trust has now been ...
Integrating collaborative filtering and matching-based search for product recommendations
Currently, recommender systems (RS) have been widely applied in many commercial e-commerce sites to help users deal with the information overload problem. Recommender systems provide personalized recommendations to users and, thus, help in making good ...
Comments