|
|
Improved collaborative filtering algorithm based
on heat conduction |
Qiang GUO 1, Jianguo LIU 2, Binghong WANG 3, |
1.Business School,
University of Shanghai for Science and Technology, Shanghai 200093,
China;Department of Physics,
University of Fribourg, Chemin du Musée 3, CH-1700, Switzerland; 2.Research Center
of Complex Systems Science, Shanghai University of Science and Technology,
Shanghai 200093, China;Department of Modern
Physics, University of Science and Technology of China, Hefei 230026,
China;Department of Physics,
University of Fribourg, Chemin du Musée 3, CH-1700, Switzerland; 3.Research Center
of Complex Systems Science, Shanghai University of Science and Technology,
Shanghai 200093, China;Department of Modern
Physics, University of Science and Technology of China, Hefei 230026,
China; |
|
|
Abstract In this paper, we present an improved collaborative filtering (ICF) algorithm by using the heat diffusion process to generate the user correlation. This algorithm has remarkably higher accuracy than the standard collaborative filtering (CF) using Pearson correlation. Furthermore, we introduce a free parameter β to regulate the contributions of objects to user correlation. The numerical simulation results indicate that decreasing the influence of popular objects can further improve the algorithmic accuracy and diversity.
|
Keywords
recommendation algorithm
collaborative filtering
heat conduction
|
Issue Date: 05 September 2009
|
|
|
Pastor-Satorras R, Vespignani A. Evolution and Structure ofthe Interent. Canbridge: Cambridge UniversityPress, 2004
|
|
Broder A, Kumar R, Moghoul F, et al. Graph structure in the web. Computer Networks, 2000, 33: 309―320
doi: 10.1016/S1389-1286(00)00083-9
|
|
Resnick P, Varian H R. Recommender systems. Communications of the ACM, 1997, 40: 56―58
doi: 10.1145/245108.245121
|
|
Brin S, Page L. The anatomy of a large-scalehypertextual Web search engine. ComputerNetworks and ISDN Systems, 1998, 30: 107―117
doi: 10.1016/S0169-7552(98)00110-X
|
|
Kleinberg J M. Authoritative sources in a hyperlinked environment. Journal of the ACM, 1999, 46: 604―632
doi: 10.1145/324133.324140
|
|
Schafer J B, Konstan J A, Riedl J. E-commerce recommender applications. Data Mining and Knowledge Discovery, 2001, 5: 115―152
doi: 10.1023/A:1009804230409
|
|
Linden G, Smith B, York J. Amazon.com recommendations: item-toitem collaborativefiltering. IEEE Internet Computing, 2003, 7: 76―80
doi: 10.1109/MIC.2003.1167344
|
|
Billsus D, Brunk C A, Evans C, et al. Adaptive interfaces for ubiquitous web access. Communications of the ACM, 2002, 45: 34―38
doi: 10.1145/506218.506240
|
|
Burke R. Hybridrecommender systems: survey and experiments. User Modeling and User-Adapted Interaction, 2002, 12: 331―370
doi: 10.1023/A:1021240730564
|
|
Adomavicius G, Tuzhilin A. Toward the next generationof recom mender systems: a survey of the state-of-the-art and possibleextensions. IEEE Transactions on Knowledgeand Data Engineering, 2005, 17: 734―749
doi: 10.1109/TKDE.2005.99
|
|
Liu J-G, Chen M Z Q, Chen J, et al. Recent advances in personal recommendation systems. International Journal of Information and SystemsScience, 2009, 5(2): 230―247
|
|
Herlocker J L, Konstan J A, Terveen K, et al. Evaluating collaborative filtering recommendersystems. ACM Transactions on InformationSystems, 2004, 22: 5―53
doi: 10.1145/963770.963772
|
|
Konstan J A, Miller B N, Maltz D, et al. GroupLens: applying collaborative filteringto usenet news. Communications of the ACM, 1997, 40: 77―87
doi: 10.1145/245108.245126
|
|
Balabanovíc M, Shoham Y. Learning information retrievalagents: experiments with automated web browsing. Communications of the ACM, 1997, 40: 66―70
|
|
Pazzani M J. Detecting change in categorical data: mining contrast sets. Artificial Intelligence Review, 1999, 13: 393―408
doi: 10.1023/A:1006544522159
|
|
Billsus D, Pazzani M. Learning collaborative informationfilters. In: Proceedings of the FifteenthInternational Conference on Machine Learning. Madison, 1998
|
|
Sarwar B, Karypis G, Konstan J, Riedl J. Applicationof dimensionality reduction in recommender system–A case study. In: Proceedings of the WebKDD 2000 Web Mining forE-Commerce Workshop at ACM SIGKDD. Boston, 2000, TR 00―043
|
|
Ren J, Zhou T, Zhang Y C. Information filtering via self-consistent refinement. Europhysics Letters, 2008, 80: 58007
doi: 10.1209/0295-5075/82/58007
|
|
Goldberg K, Roeder T, Gupta D, et al. Eigentaste: a constant time collaborative filteringalgorithm. Information Retrieval, 2001, 4: 133―151
doi: 10.1023/A:1011419012209
|
|
Zhang Y C, Blattner M, Yu Y K. Heat conduction process on community networks as a recommendationmodel. Physical Review Letters, 2007, 99: 154301
doi: 10.1103/PhysRevLett.99.154301
|
|
Zhang Y C, Medo M, Ren J, et al. Recommendation model based on opinion diffusion. Europhysics Letters, 2007, 80: 68003
doi: 10.1209/0295-5075/80/68003
|
|
Zhou T, Ren J, Medo M, et al. Bipartite network projection and personal recommendation. Physical Review E, 2007, 76: 046115
doi: 10.1103/PhysRevE.76.046115
|
|
Zhou T, Jiang L L, Su R Q, et al. Effect of initial configuration on network-basedrecommendation. Europhysics Letters, 2008, 81:58004
doi: 10.1209/0295-5075/81/58004
|
|
Huang Z, Chen H, Zeng D. Applying associative retrieval techniques to alleviatethe sparsity problem in collaborative filtering. ACMTransactions on Information Systems, 2004, 22: 116―142
doi: 10.1145/963770.963775
|
|
Sarwar B, Karypis G, Konstan J, et al. Analysis of recommendation algorithms for E-commerce. In: Proceedings of the ACM Conference on ElectronicCommerce. ACM, New York, 2000, 158―167
|
|
Liu J G, Wang B H, Guo Q. Improved collaborative filtering algorithm via informationtransformation. International Journal ofModern Physics C, 2009, 20: 285―293
doi: 10.1142/S0129183109013613
|
|
Liu J G, Zhou T, Wang B H, et al. Highly accurate recommendation algorithm basedon high-order similarities. 2008, arXiv: 0808.3726
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|