华东师范大学学报（自然科学版） >

2017 , Vol. 2017 >Issue 5: 101 - 116,137

DOI: https://doi.org/10.3969/j.issn.1000-5641.2017.05.010

用户行为分析

跨领域推荐技术综述

  • 陈雷慧 ,
  • 匡俊 ,
  • 陈辉 ,
  • 曾炜 ,
  • 郑建兵 ,
  • 高明
展开
  • 1. 华东师范大学 数据科学与工程学院, 上海 200062;
    2. 深圳腾讯计算机系统有限公司, 北京 100080
陈雷慧,女,硕士研究生,研究方向为用户行为分析、点击率预测.E-mail:15720622991@163.com

收稿日期: 2017-06-20

  网络出版日期: 2017-09-25

基金资助

国家重点研发计划（2016YFB1000905）；国家自然科学基金广东省联合重点项目（U1401256）；国家自然科学基金（61402177，61672234，61402180，61502236，61363005，61472321）

收起

Techniques for cross-domain recommendation:A survey

  • CHEN Lei-hui ,
  • KUANG Jun ,
  • CHEN Hui ,
  • ZENG Wei ,
  • ZHENG Jian-bing ,
  • GAO Ming
Expand
  • 1. School of Data Science and Engineering, East China Normal University, Shanghai 200062, China;
    2. Shenzhen Tencent Computer System Co. Ltd., Beijing 100080, China

Received date: 2017-06-20

  Online published: 2017-09-25

Fold

摘要

随着信息技术和互联网的飞速发展，信息过载的问题日趋严重.个性化推荐系统是解决这一问题的热门技术.推荐系统的核心在于推荐算法，在过去的十年里，基于单领域的协同过滤推荐算法应用最为广泛.但用户和项目数量的急剧增长使得传统的协同过滤推荐算法面临冷启动和数据稀疏问题的挑战.跨领域推荐旨在整合来自不同领域的用户偏好特征，针对每个用户自身特点进行智能化感知，精准满足用户个性化需求，从而提高目标领域推荐结果的准确性和多样性，现已成为推荐系统研究领域中的热门话题.本文首先对跨领域推荐技术进行系统地研究和分析，概述跨领域推荐算法的相关概念、技术难点；其次对现有的跨领域推荐技术进行分类，总结出各自的优点及不足；最后对跨领域推荐算法的性能分析方法进行详尽的介绍.

关键词： 信息过载; 个性化; 跨领域推荐算法

本文引用格式

陈雷慧 , 匡俊 , 陈辉 , 曾炜 , 郑建兵 , 高明 . 跨领域推荐技术综述[J]. 华东师范大学学报（自然科学版）, 2017 , 2017(5) : 101 -116,137 . DOI: 10.3969/j.issn.1000-5641.2017.05.010

Abstract

With the rapid development of information technology and Internet, the available information on the Internet has overwhelmed the human processing capabilities in some commercial applications. Personalized recommendation system is a popular technology to deal with the information overload and recommendation algorithms are the core of it. In the past decades, collaborative filtering recommendation algorithm based on single domain has been widely used in many applications. However, the problems of cold start and data sparsity usually result in overfitting and fail to give desirable performance. The cross-domain recommendation techniques have been a hot topic in the field of recommender systems, which aim to utilize knowledge from related domains to perform or improve recommendation in the target domain. This paper carries out a systematic study and analysis of cross-domain recommendation techniques. First, we summarize the related concepts and the technical difficulties of cross-domain recommendation algorithms. Second, we present a general categorization of cross-domain recommendation techniques and sum up their respective advantages and disadvantages. Finally we introduce the method of performance analysis of cross-domain recommendation algorithm in detail.

Key words： information overload; personalization; cross-domain recommendation algorithms

参考文献

[1] LI B, YANG Q, XUE X. Can movies and books collaborate? Cross-domain collaborative filtering for sparsity reduction.[C]//Proceedings of the International Joint Conference on Artificial Intelligence.USA:DBLP, 2009:2052-2057.
[2] CANTADOR I, FERNáNDEZ-TOBíAS I, BERKOVSKY S, et al. Cross-Domain Recommender Systems[M]//Recommender Systems Handbook. US:Springer, 2015:919-959.
[3] ZHAO L, XIANG E W, XIANG E W, et al. Active transfer learning for cross-system recommendation[C]//Twenty-Seventh AAAI Conference on Artificial Intelligence. USA:AAAI Press, 2013:1205-1211.
[4] PAN W, XIANG E W, YANG Q. Transfer learning in collaborative filtering with uncertain ratings[C]//TwentySixth AAAI Conference on Artificial Intelligence. USA:AAAI Press, 2012:662-668.
[5] LI B. Cross-domain collaborative filtering:A brief survey[C]//IEEE, International Conference on TOOLS with Artificial Intelligence.[S.l.]:IEEE Computer Society, 2011:1085-1086.
[6] 罗浩. 基于跨域信息推荐的算法研究[D]. 北京:北京邮电大学, 2014.
[7] FERNÁNDEZ-TOB ÍAS I, CANTADOR I, KAMINSKAS M, et al. Cross-domain recommender systems:A survey of the State of the Art[C]//Proc 2nd Spanish Conf Inf Retrieval.[S.l.]:[S.n.], 2012:187-198.
[8] LI B, YANG Q, XUE X. Transfer learning for collaborative filtering via a rating-matrix generative model[C]//International Conference on Machine Learning, ICML 2009. Canada:DBLP, 2009:617-624.
[9] WINOTO P, TANG T. If you like the Devil Wears Prada the book, will you also enjoy the Dvil Wears Prada the movie? A study of cross-domain recommendations[J]. New Generation Computing, 2008, 26(3):209-225.
[10] BERKOVSKY S, KUFLIK T, RICCI F. Mediation of user models for enhanced personalization in recommender systems[J]. User Modeling and User-Adapted Interaction, 2008, 18(3):245-286.
[11] BERKOVSKY S, KUFLIK T, RICCI F. Cross-domain mediation in collaborative filtering[C]//User Modeling 2007, International Conference. Greece:DBLP, 2007:355-359.
[12] SINGH, AJIT P, GORDON, et al. Relational learning via collective matrix factorization[J]. Relational Learning via Collective Matrix Factorization, 2008:650-658.
[13] PAN W, YANG Q. Transfer learning in heterogeneous collaborative filtering domains[J]. Artificial Intelligence, 2013, 197(4):39-55.
[14] XIN X, LIU Z, LIN C Y, et al. Cross-domain collaborative filtering with review text[C]//International Conference on Artificial Intelligence. USA:AAAI Press, 2015:1827-1833.
[15] WEI C, HSU W, LEE M L. A unified framework for recommendations based on quaternary semantic analysis[C]//International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM, 2011:1023-1032.
[16] ARORA A, TANEJA V, PARASHAR S, et al. Cross-domain based event recommendation using tensor factorization[J]. Open Computer Science, 2016, 6(1):32-37.
[17] HU L, CAO J, XU G, et al. Personalized recommendation via cross-domain triadic factorization[J]. Proc 22nd Int World Wide Web Conf, 2014:595-606.
[18] ZHOU G, HE Z, ZHANG Y, et al. Canonical polyadic decomposition:From 3-way to N-way[C]//Eighth International Conference on Computational Intelligence and Security.[S.l.]:IEEE, 2012:391-395.
[19] SCHMITZ S K, HASSELBACH P P, EBISCH B, et al. Application of parallel factor analysis (PARAFAC) to electrophysiological data.[J]. Front Neuroinform, 2014(8):84.
[20] KIERS H A L. An alternating least squares algorithm for PARAFAC2 and three-way DEDICOM[J]. Computational Statistics & Data Analysis, 1993, 16(1):103-118.
[21] SONG T, PENG Z, WANG S, et al. Review-based cross-domain recommendation through joint tensor factorization[C]//Database Systems for Advanced Applications.[S.l.]:DASFAA, 2017:525-540.
[22] LI H, LIN R, HONG R, et al. Generative models for mining latent aspects and their ratings from short reviews[C]//2015 IEEE International Conference on Data Mining. USA:IEEE, 2015:241-250.
[23] JIANG M, CUI P, CHEN X, et al. Social recommendation with cross-domain transferable knowledge[J]. IEEE Transactions on Knowledge & Data Engineering, 2015, 27(11):3084-3097.
[24] YANG D, HE J, QIN H, et al. A graph-based recommendation across heterogeneous domains[J]. 2016:1075-1080.
[25] ZHANG J, YU P S. Multiple anonymized social networks alignment[C]//IEEE International Conference on Data Mining.[S.l.]:IEEE Computer Society, 2015:599-608.
[26] KOUTRA D, TONG H, LUBENSKY D. BIG-ALIGN:Fast bipartite graph alignment[C]//IEEE International Conference on Data Mining.[S.l.]:IEEE, 2013:389-398.
[27] LI C Y, LIN S D. Matching Users and Items Across Domains to Improve the Recommendation Quality[M]. New York:ACM, 2014:801-810.
[28] SHI Y, LARSON M, HANJALIC A. Tags as bridges between domains:Improving recommendation with taginduced cross-domain collaborative filtering[C]//User Modeling, Adaption and Personalization, International Conference. USA:DBLP, 2011:305-316.
[29] SALAKHUTDINOV R, MNIH A. Probabilistic matrix factorization[C]//International Conference on Neural Information Processing Systems. USA:Curran Associates, 2007:1257-1264.
[30] DING C, LI T, PENG W, et al. Orthogonal nonnegative matrix t-factorizations for clustering[J]. Proc 12th ACM SIGKDD, 2006:126-135.
[31] CHEN W, HSU W, LEE M L. Making recommendations from multiple domains[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. USA:ACM, 2013:892-900.
[32] REN S, GAO S, LIAO J, et al. Improving cross-domain recommendation through probabilistic cluster-level latent factor model[C]//Twenty-Ninth AAAI Conference on Artificial Intelligence. USA:AAAI Press, 2015:4200-4201.
[33] GAO S, LUO H, CHEN D, et al. Cross-domain recommendation via cluster-level latent factor model[C]//Proceedings, Part Ⅱ, of the European Conference on Machine Learning and Knowledge Discovery in Databases. New York:Springer-Verlag, 2013:161-176.
[34] MORENO O, SHAPIRA B, ROKACH L, et al. TALMUD:transfer learning for multiple domains[C]//ACM International Conference on Information and Knowledge Management. New York:ACM, 2012:425-434.
[35] CHUNG R, SUNDARAM D, SRINIVASAN A. Integrated personal recommender systems[C]//International Conference on Electronic Commerce:the Wireless World of Electronic Commerce. USA:DBLP, 2007:65-74.
[36] SZOMSZOR M, ALANI H, CANTADOR I, et al. Semantic Modelling of User Interests Based on CrossFolksonomy Analysis[M]. Germany:Springer Berlin Heidelberg, 2008:632-648.
[37] ABEL F, HERDER E, HOUBEN G J, et al. Cross-system user modeling and personalization on the social web[J]. User Modeling and User-Adapted Interaction, 2013, 23(2-3):169-209.
[38] FERNÁNDEZ-TOBíAS I, CANTADOR I, PLAZA L. An emotion dimensional model based on social tags:Crossing folksonomies and enhancing recommendations[J]. Lecture Notes in Business Information Processing, 2013, 152:88-100.
[39] BLEI D M, NG A Y, JORDAN M I. Latent dirichlet allocation[M]. J Mach Learn Res, 2003(3):993-1022.
[40] KUMAR A, KUMAR N, HUSSAIN M, et al. Semantic clustering-based cross-domain recommendation[C]//Computational Intelligence and Data Mining.[S.l.]:IEEE, 2014:137-141.
[41] LOIZOU A. How to recommend music to film buffs:Enabling the provision of recommendations from multiple domains[J]. University of Southampton, 2009.
[42] KAMINSKAS M, RICCI F. A generic semantic-based framework for cross-domain recommendation[C]//International Workshop on Information Heterogeneity and Fusion in Recommender Systems. New York:ACM, 2011:25-32.
[43] KAMINSKAS M, FERNÁNDEZ-TOB ÍAS I, CANTADOR I, et al. Ontology-Based Identification of Music for Places[M]//Information and Communication Technologies in Tourism. Germany:Springer Berlin Heidelberg, 2013:436-447.
[44] HEITMANN B, HAYES C. SemStim at the LOD-RecSys 2014 Challenge[M]//Semantic Web Evaluation Challenge. Germany:Springer International Publishing, 2014:170-175.
[45] JIANG M, CUI P, YUAN N J, et al. Little is much:bridging cross-platform behaviors through overlapped crowds[C]//Thirtieth AAAI Conference on Artificial Intelligence. USA:AAAI Press, 2016:13-19.
[46] SHAPIRA B, ROKACH L, FREILIKHMAN S. Facebook single and cross domain data for recommendation systems[J]. User Modeling and User-Adapted Interaction, 2013, 23(2/3):211-247.
[47] TIROSHI A, KUFLIK T. Domain Ranking for Cross Domain Collaborative Filtering[M]//User Modeling, Adaptation, and Personalization. Germany:Springer Berlin Heidelberg, 2012:328-333.
[48] NAKATSUJI M, FUJIWARA Y, TANAKA A, et al. Recommendations over domain specific user graphs[C]//European Conference on Artificial Intelligence. USA:DBLP, 2010:607-612.
[49] TIROSHI A, BERKOVSKY S, KAAFAR M A, et al. Cross social networks interests predictions based ongraph features[C]//ACM Conference on Recommender Systems. New York:ACM, 2013:319-322.
[50] KRISHNAMURTHY B, PURI N, GOEL R. Learning vector-space representations of items for recommendations using word embedding models[J]. Procedia Computer Science, 2016, 80:2205-2210.
[51] PEROZZI B, ALRFOU R, SKIENA S. Deepwalk:Online learning of social representations[C]//The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York:ACM, 2014:701-710.
[52] GROVER A, LESKOVEC J. node2vec:Scalable feature learning for networks[C]//ACM SIGKDD International Conference. New York:ACM, 2016:855-864.
[53] WANG D, CUI P, ZHU W. Structural deep network embedding[C]//ACM SIGKDD International Conference. New York:ACM, 2016:1225-1234.
[54] TANG J, QU M, WANG M, et al. LINE:Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web.[S.l.]:International World Wide Web Conference Committee, 2015:1067-1077.
[55] CAO S, LU W, XU Q. GraRep:Learning graph representations with global structural information[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management. New York:ACM, 2015:891-900.
[56] LI C, WANG S, YANG D, et al. PPNE:Property Preserving Network Embedding[C]//Database Systems for Advanced Applications,22nd International Conference.[S.l.]:DASFAA, 2017:163-179.
[57] LI C, LI Z, WANG S, et al. Semi-supervised network embedding[C]//Database Systems for Advanced Applications, 22nd International Conference.[S.l.]:DASFAA, 2017:131-147.
[58] 项亮.推荐系统实践[M]. 北京:人民邮电出版社, 2012.
[59] SHANI G, GUNAWARDANA A. Evaluating Recommendation Systems[M]//Recommender Systems Handbook, 2011:257-297.
[60] SAHEBI S, BRUSILOVSKY P. Cross-Domain Collaborative Recommendation in a Cold-Start Context:The Impact of User Profile Size on the Quality of Recommendation[M]. Germany:Springer,2013:289-295.
Options
文章导航

/

〈 〉