Please wait a minute...
浙江大学学报(工学版)  2019, Vol. 53 Issue (1): 89-98    DOI: 10.3785/j.issn.1008-973X.2019.01.010
计算机技术     
基于社交信息和物品曝光度的矩阵分解推荐
韩勇1, 宁连举1, 郑小林2, 林炜华2, 孙中原1
1. 北京邮电大学 经济管理学院, 北京 100876;
2. 浙江大学 计算机科学与技术学院, 浙江 杭州 310058
Matrix factorization recommendation based on social information and item exposure
HAN Yong1, NING Lian-ju1, ZHENG Xiao-lin2, LIN Wei-hua2, SUN Zhong-yuan1
1. School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China
 全文: PDF(998 KB)   HTML
摘要:

为了解决隐式反馈推荐中的数据稀疏性和未观测值二义性,提出基于社交信息和物品曝光度的概率矩阵分解推荐算法. 该算法通过对用户-用户社交矩阵进行矩阵分解来约束用户偏好潜在因子,一定程度上缓解了数据稀疏性问题;将物品曝光度作为观测值的条件,结合物品本身的流行度和用户的社交信息,对物品曝光度进行建模,解决未观测值的二义性. 在Lastfm公开数据集上开展多个层次的实验和分析. 结果表明,与已有的隐式推荐算法相比,在召回率、平均准确率(MAP)和归一化折损累计增益(NDCG)3个评价标准上都有一定程度的提高.

Abstract:

A probabilistic matrix factorization model was proposed based on social information and item exposure in order to solve the problem of data sparsity and ambiguity of unobserved data in implicit feedback recommendation. The model constrained users' potential preference factor by decomposing the user-user social matrix to alleviate data sparseness to some extent. The item exposure was taken as the condition of the observation value, and the item exposure was modeled based on the popularity of the item itself and the social information of the user in order to resolve the ambiguity of the unobserved data. Multiple levels experiments and analysis were conducted on Lastfm dataset. Results show that the proposed model can improve the performance on metrics of recall, mean average precision (MAP) and normalized discounted cumulative gain (NDCG) compared to state-of-art implicit feedback algorithms.

收稿日期: 2018-04-20 出版日期: 2019-01-07
CLC:  TP391  
基金资助:

国家自然科学基金资助项目(71271032);北京市自然科学基金资助项目(9182012)

通讯作者: 宁连举,男,教授.orcid.org/0000-0002-2353-1117.     E-mail: ninglj007@126.com
作者简介: 韩勇(1980-),男,博士生,从事互联网金融、用户行为分析及数据挖掘研究.orcid.org/0000-0001-5804-408X.E-mail:517840159@qq.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

韩勇, 宁连举, 郑小林, 林炜华, 孙中原. 基于社交信息和物品曝光度的矩阵分解推荐[J]. 浙江大学学报(工学版), 2019, 53(1): 89-98.

HAN Yong, NING Lian-ju, ZHENG Xiao-lin, LIN Wei-hua, SUN Zhong-yuan. Matrix factorization recommendation based on social information and item exposure. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2019, 53(1): 89-98.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.01.010        http://www.zjujournals.com/eng/CN/Y2019/V53/I1/89

[1] PAZZANI M J, BILLSUS D. Content-based recommendation systems[M]//The adaptive web. Berlin:Springer, 2007:325-341.
[2] 李伟霖, 王成良, 文俊浩. 基于评论与评分的协同过滤算法[J]. 计算机应用研究, 2017, 34(2):361-364 LI Wei-lin, WANG Cheng-liang, WEN Jun-hao. Reliability analysis of manipulator based on fourth-moment estimation[J]. Application Research of Computers, 2017, 34(2):361-364
[3] DESROSIERS C, KARYPIS G. A comprehensive survey of neighborhood-based recommendation methods[M]//Recommender systems handbook. Boston:Springer, 2011:107-144.
[4] 李博, 陈志刚, 黄瑞, 等. 基于LDA模型的音乐推荐算法[J]. 计算机工程, 2016, 42(6):175-179 LI Bo, CHEN Zhi-gang, HUANG Rui, et al. Music recommendation algorithm based on LDA model[J]. Computer Engineering, 2016, 42(6):175-179
[5] CHEN C, ZHENG X, WANG Y, et al. Context-aware collaborative topic regression with social matrix factorization for recommender systems[C]//28th AAAI Conference on Artificial Intelligence. Québec:AAAI, 2014, 14:9-15.
[6] PATEREK A. Improving regularized singular value decomposition for collaborative filtering[C]//Proceedings of KDD Cup and Workshop. San Jose:ACM, 2007:5-8.
[7] KOREN Y. Factorization meets the neighborhood:a multifaceted collaborative filtering model[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Las Vegas:ACM, 2008:426-434.
[8] KOREN Y. Collaborative filtering with temporal dynamics[J]. Communications of the ACM, 2010, 53(4):89-97.
[9] MNIH A, SALAKHUTDINOV R R. Probabilistic matrix factorization[C]//Advances in Neural Information Processing Systems. Vancouver:ACM, 2007:1257-1264.
[10] LIANG D, ALTOSAAR J, CHARLIN L, et al. Factorization meets the item embedding:regularizing matrix factorization with item co-occurrence[C]//Proceedings of the 10th ACM Conference on Recommender Systems. Boston:ACM, 2016:59-66.
[11] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR:Bayesian personalized ranking from implicit feedback[C]//Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. Montreal:UAI Press, 2009:452-461.
[12] YU L, ZHOU G, ZHANG C, et al. Rankmbpr:rank-aware mutual Bayesian personalized ranking for item recommendation[C]//International Conference on Web-Age Information Management. Nanchang:WAIM, 2016:244-256.
[13] ZHANG H, GANCHEV I, NIKOLOV N S, et al. Weighted matrix factorization with Bayesian personalized ranking[C]//SAI Computing Conference. London:SAI, 2017.
[14] HU Y, KOREN Y, VOLINSKY C. Collaborative filtering for implicit feedback datasets[C]//8th IEEE International Conference on Data Mining. Taipei:IEEE, 2008:263-272.
[15] HE X, ZHANG H, KAN M Y, et al. Fast matrix factorization for online recommendation with implicit feedback[C]//Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval. Pisa:ACM, 2016:549-558.
[16] LIANG D, CHARLIN L, MCINERNEY J, et al. Modeling user exposure in recommendation[C]//Proceedings of the 25th International Conference on World Wide Web. Montréal:International World Wide Web Conferences Steering Committee, 2016:951-961.
[17] LIN X, ZHANG M, ZHENG Y F, et al. Learning and transferring social and item visibilities for personalized recommendation[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. Singapore:ACM, 2017:337-346.
[18] PURUSHOTHAM S, LIU Y, KUO C C J. Collaborative topic regression with social matrix factorization for recommendation systems[C]//International Conference on International Conference on Machine Learning. Edinburgh:Omni Press, 2012.
[19] JAMALI M, ESTER M. A matrix factorization technique with trust propagation for recommendation in social networks[C]//Proceedings of the 4th ACM Conference on Recommender Systems. Barcelona:ACM, 2010:135-142.
[20] MA H, ZHOU T C, LYU M R, et al. Improving recommender systems by incorporating social contextual information[J]. ACM Transactions on Information Systems (TOIS), 2011, 29(2):1-23.
[21] HU G N, DAI X Y, QIU F Y, et al. Collaborative filtering with topic and social latent factors incorporating implicit feedback[J]. ACM Transactions on Knowledge Discovery from Data (TKDD), 2018, 12(2):23.
[22] GUO G, ZHANG J, ZHU F, et al. Factored similarity models with social trust for top-N item recommendation[J]. Knowledge-Based Systems, 2017, 122:17-25.
[23] 柳玲, 马艺, 文俊浩, 等. 基于用户影响力游走模型的社会化推荐算法[J]. 计算机工程与应用, 2017(10):61-67 LIU Ling, MA Yi, WEN Jun-hao, et al. Social recommendation algorithm based on user influence walk model[J]. Computer Engineering and Applications, 2017(10):61-67
[24] CHANEY A J B, BLEI D M, ELIASSI-RAD T. A probabilistic model for using social networks in personalized item recommendation[C]//Proceedings of the 9th ACM Conference on Recommender Systems. Vienna:ACM, 2015:43-50.
[25] GOPALAN P, HOFMAN J M, BLEI D M. Scalable recommendation with hierarchical poisson factorization[C]//Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence. Amsterdam:UAI, 2015:326-335.
[26] DUHAN N, SHARMA A K, BHATIA K K. Page ranking algorithms:a survey[C]//IEEE International Conference on Advance Computing. Patiala:IEEE, 2009:1530-1537.
[27] Lastfm data set[EB/OL].[2018-03-22]. https://grouplens.org/datasets/hetrec-2011/.

[1] 郑洲, 张学昌, 郑四鸣, 施岳定. 基于区域增长与统一化水平集的CT肝脏图像分割[J]. 浙江大学学报(工学版), 2018, 52(12): 2382-2396.
[2] 赵丽科, 郑顺义, 王晓南, 黄霞. 单目序列的刚体目标位姿测量[J]. 浙江大学学报(工学版), 2018, 52(12): 2372-2381.
[3] 何杰光, 彭志平, 崔得龙, 李启锐. 局部维度改进的教与学优化算法[J]. 浙江大学学报(工学版), 2018, 52(11): 2159-2170.
[4] 李志, 单洪, 马涛, 黄郡. 基于反向标签传播的移动终端用户群体发现[J]. 浙江大学学报(工学版), 2018, 52(11): 2171-2179.
[5] 王硕朋, 杨鹏, 孙昊. 听觉定位数据库构建过程优化[J]. 浙江大学学报(工学版), 2018, 52(10): 1973-1979.
[6] 魏小峰, 程承旗, 陈波, 王海岩. 基于独立边数的链码方法[J]. 浙江大学学报(工学版), 2018, 52(9): 1686-1693.
[7] 陈荣华, 王鹰汉, 卜佳俊, 于智, 高斐. 基于KNN算法与局部回归的网站无障碍采样评估[J]. 浙江大学学报(工学版), 2018, 52(9): 1702-1708.
[8] 张承志, 冯华君, 徐之海, 李奇, 陈跃庭. 图像噪声方差分段估计法[J]. 浙江大学学报(工学版), 2018, 52(9): 1804-1810.
[9] 刘洲洲, 李士宁, 李彬, 王皓, 张倩昀, 郑然. 基于弹性碰撞优化算法的传感云资源调度[J]. 浙江大学学报(工学版), 2018, 52(8): 1431-1443.
[10] 王勇超, 祝凯林, 吴奇轩, 鲁东明. 基于局部渲染的高精度模型自适应展示技术[J]. 浙江大学学报(工学版), 2018, 52(8): 1461-1466.
[11] 孙念, 李玉强, 刘爱华, 刘春, 黎威威. 基于松散条件下协同学习的中文微博情感分析[J]. 浙江大学学报(工学版), 2018, 52(8): 1452-1460.
[12] 郑守国, 崔雁民, 王青, 杨飞, 程亮. 飞机装配现场数据采集平台设计[J]. 浙江大学学报(工学版), 2018, 52(8): 1526-1534.
[13] 毕晓君, 王朝. 基于超平面投影的高维多目标进化算法[J]. 浙江大学学报(工学版), 2018, 52(7): 1284-1293.
[14] 张廷蓉, 滕奇志, 李征骥, 卿粼波, 何小海. 岩心三维CT图像超分辨率重建[J]. 浙江大学学报(工学版), 2018, 52(7): 1294-1301.
[15] 赵传松, 任红格, 史涛, 李福进. 内在动机轮式倒立摆反应式认知系统[J]. 浙江大学学报(工学版), 2018, 52(6): 1073-1080.