《计算机应用研究》|Application Research of Computers

基于时序逆影响的随机游走推荐算法

Temporal inverse influence based recommendation method by using random walk

免费全文下载 (已被下载 次)  
获取PDF全文
作者 肖春景,夏克文,乔永卫
机构 1.河北工业大学 电子信息工程学院,天津 300300;2.中国民航大学 a.计算机科学与技术学院;b.工程技术训练中心,天津 300300
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)08-2304-04
DOI 10.3969/j.issn.1001-3695.2018.08.016
摘要 相似性计算是协同过滤推荐的关键步骤。针对传统相似性计算认为相似关系是对等的且没有考虑消费顺序和时间间隔的问题,提出了基于时序逆影响的随机游走推荐算法。首先,基于用户时序关联图提出一种新的称为时序逆影响的相似性度量,利用随机游走得到了目标用户近邻集合;其次,利用随机游走在项目时序关联图上进一步改进推荐的多样性和覆盖率。它不但认为用户间相似是不对称的,考虑了用户消费项目的顺序和时间间隔,获得了用户全局的直接和间接近邻,而且考虑了项目间的时序逆影响。通过在真实数据集上的大量实验结果表明,与其他随机游走方法相比,其不但能提高推荐性能、缓解数据稀疏,而且通过提高多样性和覆盖率解决了过拟合的问题。
关键词 相似性计算;随机游走;时序信息;时序关联图;协同过滤
基金项目 国家自然科学基金资助项目(U1533104)
河北省自然科学基金资助项目(E2016202341)
天津市自然科学基金资助项目(14JCZDJC32500)
中央高校基本科研业务费专项资金资助项目(ZXH2012P009)
本文URL http://www.arocmag.com/article/01-2018-08-016.html
英文标题 Temporal inverse influence based recommendation method by using random walk
作者英文名 Xiao Chunjing, Xia Kewen, Qiao Yongwei
机构英文名 1.SchoolofElectronic&InformationEngineering,HebeiUniversityofTechnology,Tianjin300300,China;2.a.SchoolofComputerScience&Technology,b.Engineering&TechnicalTrainingCenter,CivilAviationUniversityofChina,Tianjin300300,China
英文摘要 Similarity computation is a very critical step in traditional collaborative filtering (CF) recommendation.However, traditional similarity always thought that the relationships are symmetric and rarely considered the order of common consumed items and the time interval of them.To get better recommendation performance, this paper proposed a random walk based recommendation method based on temporal inverse influence.It firstly proposed a new similarity measurement called temporal inverse influence on user temporal correlation graph and selected the similar users who most influenced on the target user using random walk with restart.Secondly, it used the item temporal correlation graph to further improve the diversity and coverage of CF recommendation results.It not only thinks that the influence is asymmetric, takes the order of common consumed items of users and the time interval of them into account to find direct and indirect neighbors from a global perspective, but also considers the inverse influence between items to improve the recommendation results.The experimental results on a real dataset show that this proposed method can not only achieve better recommendation performance, but also alleviate data sparsity and tackle the over fitting problem by getting better coverage and diversity compared to several random-walk-based methods.
英文关键词 similarity computation; random walk(RW); temporal information; temporal relation graph; collaborative filtering
参考文献 查看稿件参考文献
  [1] Zhang Lisheng, Deng Xiaoliang, Lei Dajiang. Collaborative filtering recommendation algorithm based on user interest characteristics and item category[J] . Journal of Computational Information Systems, 2013, 19(15):5973-5986.
[2] Fouss F, Pirotte A, Renders J M, et al. Random-walk computation of similarities between nodes of a graph with application to collaborative recommendation[J] . IEEE Trans on Knowledge and Engineering, 2007, 19(3):355-369.
[3] Zhang Zhu, Zeng D D, Abbasi A, et al. A random walk model for item recommendation in social tagging systems[J] . ACM Trans on Management Information Systems, 2013, 4(2):8-24.
[4] Feng Shanshan, Cao Jian. Improving group recommendations via detecting comprehensive correlative information[J] . Multimedia Tools and Applications, 2017, 76(1):1355-1377.
[5] Feng Weisi, Jing Chenyang, Li Li. Recommender system based on random walk with topic model[C] //Proc of the 6th International Advanced Computing Conference. Piscataway, NJ:IEEE Press, 2016:727-732.
[6] 单晓菲, 米传民, 马静. 基于选择性随机游走的协同过滤推荐算法研究[C] //第十六届中国管理科学学术年会论文集. 2014:73-78.
[7] Ying J J C, Kuo Wenning, Tseng V S, et al. Mining user check-in behavior with a random walk for urban point-of-interest recommendations[J] . ACM Trans on Intelligent Systems and Technology, 2014, 5(3):40-66.
[8] Xu Guangdong, Fu Bin, Gu Yanhui. Point-of-interest recommendations via a supervised random walk algorithm[J] . IEEE Intelligent Systems, 2016, 31(1):15-23.
[9] Bagci H, Karagoz P. Random walk based context-aware activity recommendation for location based social networks[C] //Proc of IEEE International Conference on Data Science and Advanced Analytics. Piscataway, NJ:IEEE Press, 2015.
[10] 刘梦娟, 王巍, 李杨曦, 等. AttentionRank+:一种基于关注关系与多用户行为的图推荐算法[J] . 计算机学报, 2017, 40(3):634-647.
[11] 曹云忠, 邵培基, 李良强. 基于信任随机游走模型的微博粉丝推荐[J] . 系统管理学报, 2017, 26(1):117-123.
[12] Xia Feng, Chen Zhen, Wang Wei, et al. MVCWalker:random walk-based most valuable collaborators recommendation exploiting academic factors[J] . IEEE Trans on Emerging Topics in Computing, 2014, 2(3):364-375.
[13] Wu Hao, Liu Xiaoxin, Pei Yijian, et al. Enhancing context-aware recommendation via a unified graph model[C] //Proc of International Conference on Identification, Information and Knowledge in the Internet of Things. Piscataway, NJ:IEEE Press, 2014:76-79.
[14] Yao Weilong, He Jing, Huang Guangyan, et al. A graph-based model for context-aware recommendation using implicit feedback data[J] . World Wide Web, 2015, 18(5):1351-1371.
[15] Hu Yan, Peng Qimin, Hu Xiaohui. A time-aware and data sparsity tolerant approach for Web service recommendation[C] //Proc of the 21st IEEE International Conference on Web Services. Piscataway, NJ:IEEE Press, 2014:330-340.
[16] Yu Weiren, Lin Xuemin. IRWR:incremental random walk with restart[C] //Proc of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2013:1017-1020.
[17] Xiang Liang, Yuan Quan, Zhao Shiwan, et al. Temporal recommendation on graphs via long-and short-term preference fusion[C] //Proc of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM Press, 2010:723-732.
[18] Nie Dacheng, Fu Yan, Zhou Junlin, et al. A personalized recommendation algorithm via biased random walk[C] //Proc of the 11th International Joint Conference on Computer Science and Software Engineering. Washington DC:IEEE Computer Society, 2014:292-296.
[19] Jin Zhaoyan, Wu Quanyuan, Shi Dianxi, et al. Random walk based inverse influence research in online social networks[C] //Proc of IEEE International Conference on High Performance Computing and Communication & IEEE International Conference on Embedded and Ubiquitous Computing. Washington DC:IEEE Computer Society, 2013:2206-2213.
[20] Liu N N, He Luheng, Zhao Min. Social temporal collaborative ranking for context aware movie recommendation[J] . ACM Trans on Intelligent Systems and Technology, 2013, 4(1):15-26.
[21] 孙光福, 吴乐, 刘淇, 等. 基于时序行为的协同过滤推荐算法[J] . 软件学报, 2013, 24(11):2721-2733.
[22] Yin Fengjiang, Wang Zhenwen, Tan Wentang. et al. Sparsity-tolerated algorithm with missing value recovering in user-based collaborative filtering recommendation[J] . Journal of Information & Computational Science, 2013, 10(15):4939-4948.
[23] 项亮. 推荐系统实践[M] . 北京:人民邮电出版社, 2012:23-34.
收稿日期 2017/4/21
修回日期 2017/6/8
页码 2304-2307
中图分类号 TP391.1;TP301.6
文献标志码 A