Construction and inference of latent variable model oriented to user preference discovery

doi:10.11772/j.issn.1001-9081.2017.02.0360

Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (2): 360-366.DOI: 10.11772/j.issn.1001-9081.2017.02.0360

Previous Articles Next Articles

Construction and inference of latent variable model oriented to user preference discovery

GAO Yan¹, YUE Kun¹, WU Hao¹, FU Xiaodong², LIU Weiyi¹

1. School of Information Science and Engineering, Yunnan University, Kunming Yunnan 650504, China;
2. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunnan 650500, China

Received:2016-08-12 Revised:2016-09-06 Online:2017-02-10 Published:2017-02-11
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61472345, 61562090, 61462056), the Applied Basic Research Project of Yunnan Province (2014FA023, 2014FA028), the Program of Yunnan Provincial Foundation for Leaders of Disciplines in Science and Technology (2012HB004),the Program for Excellent Young Talents in Yunnan University (XT412003), the Program for Innovative Research Team in Yunnan University (XT412011).

面向用户偏好发现的隐变量模型构建与推理

高艳¹, 岳昆¹, 武浩¹, 付晓东², 刘惟一¹

1. 云南大学信息学院, 昆明 650504;
2. 昆明理工大学信息工程与自动化学院, 昆明 650500

通讯作者: 岳昆,kyue@ynu.edu.cn
作者简介:高艳(1991-),女,云南曲靖人,硕士研究生,CCF会员,主要研究方向:知识发现、社会媒体数据分析;岳昆(1979-),男,云南曲靖人,教授,博士生导师,博士,CCF会员,主要研究方向:海量数据分析与服务;武浩(1979-),男,河南平顶山人,副教授,博士,主要研究方向:信息检索、推荐系统、服务计算;付晓东(1975-),男,云南镇雄人,教授,博士,CCF会员,主要研究方向:服务计算、智能决策;刘惟一(1950-),男,云南昆明人,教授,博士生导师,CCF会员,主要研究方向:人工智能、数据与知识工程。
基金资助:
国家自然科学基金资助项目（61472345，61562090，61462056）；云南省应用基础研究计划项目（2014FA023，2014FA028）；云南省中青年学术和技术带头人才后备人才培育计划项目（2012HB004）；云南大学青年英才培育计划项目（XT412003）；云南大学创新团队培育计划项目（XT412011）。

Abstract

Abstract: Large amount of user rating data, involving plentiful users' opinion and preference, is produced in e-commerce applications. An construction and inference method for latent variable model (i.e., Bayesian Network with a latent variable) oriented to user preference discovery from rating data was proposed to accurately infer user preference. First, the unobserved values in the rating data were filled by Biased Matrix Factorization (BMF) model to address the sparseness problem of rating data. Second, latent variable was used to represent user preference, and the construction of latent variable model based on Mutual Information (MI), maximal semi-clique and Expectation Maximization (EM) was given. Finally, an Gibbs sampling based algorithm for probabilistic inference of the latent variable model and the user preference discovery was given. The experimental results demonstrate that, compared with collaborative filtering, the latent variable model is more efficient for describing the dependence relationships and the corresponding uncertainties of related attributes among rating data, which can more accurately infer the user preference.

Key words: user preference, rating data, Bayesian network, latent variable model, probabilistic inference, biased matrix factorization

摘要： 电子商务应用中产生了大量用户评分数据，而这些数据中富含了用户观点和偏好信息，为了能够从这些数据中准确地推断出用户偏好，提出一种面向评分数据中用户偏好发现的隐变量模型（即含隐变量的贝叶斯网）构建和推理的方法。首先，针对评分数据的稀疏性，使用带偏置的矩阵分解（BMF）模型对其进行填补；其次，用隐变量表示用户偏好，给出了基于互信息（MI）、最大半团和期望最大化（EM）算法的隐变量模型构建方法；最后，给出了基于Gibbs采样的隐变量模型概率推理和用户偏好发现方法。实验结果表明，与协同过滤的方法相比，该方法能有效地描述评分数据中相关属性之间的依赖关系及其不确定性，从而能够更准确地推断出用户偏好。

关键词: 用户偏好, 评分数据, 贝叶斯网, 隐变量模型, 概率推理, 带偏置的矩阵分解

CLC Number:

GAO Yan, YUE Kun, WU Hao, FU Xiaodong, LIU Weiyi. Construction and inference of latent variable model oriented to user preference discovery[J]. Journal of Computer Applications, 2017, 37(2): 360-366.

高艳, 岳昆, 武浩, 付晓东, 刘惟一. 面向用户偏好发现的隐变量模型构建与推理[J]. 计算机应用, 2017, 37(2): 360-366.

References

[1] 高全力,高岭,杨建峰,等.上下文感知推荐系统中基于用户认知行为的偏好获取方法[J].计算机学报, 2015,38(9):1767-1776. (GAO Q L, GAO L, YANG J F, et al. A preference elicitation method based on user's cognitive behavior for context-aware recommender system[J]. Chinese Journal of Computers, 2015, 38(9):1767-1776.).
[2] LIU L, ZHU F, ZHANG L, et al. A probabilistic graphical model for topic and preference discovery on social media[J]. Neurocomputing, 2012, 95:78-88.
[3] 项亮.推荐系统实践[M].北京:人民邮电出版社,2012:196-212.(XIANG L. Practice of Recommendation System[M]. Beijing:Posts & Telecom Press, 2012:196-212.).
[4] SALAKHUTDINOV R, MNIH A. Probabilistic matrix factorization[C]//NIPS 2008:Proceedings of the 2008 Conference on Neural Information Processing Systems, Cambridge, MA:MIT Press, 2008:1257-1264.
[5] SALAKHUTDINOV R, MNIH A. Bayesian probabilistic matrix factorization using Markov chain Monte Carlo[C]//ICML'08:Proceedings of the 25th International Conference on Machine Learning. New York:ACM, 2008:880-887.
[6] KOREN Y. Factorization meets the neighborhood:a multifaceted collaborative filtering model[C]//KDD'08:Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2008:426-434.
[7] 张连文,郭海鹏.贝叶斯网引论[M].北京:科学出版社,2006:31-36,194. (ZHANG L W, GUO H P. Introduction to Bayesian Networks[M]. Beijing:Science Press, 2006:31-36, 194.).
[8] HECKERMAN D. A tutorial on learning with Bayesian networks[M]//Innovations in Bayesian Networks:Theory and Applications, Volume 156 of the Series Studies in Computational Intelligence. Berlin:Springer-Verlag, 2008:33-82.
[9] DAYE J, YEU Y K, AHN J, et al. Inference of disease-specific gene interaction network using a Bayesian network learned by genetic algorithm[C]//SAC'15:Proceedings of the 30th Annual ACM Symposium on Applied Computing. New York:ACM, 2015:47-53.
[10] ZHANG J, CORMODE G, CECILIA M, et al. PrivBayes:private data release via Bayesian networks[C]//SIGMOD'14:Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data. New York:ACM, 2014:1423-1434.
[11] WANG H, ZHAI C X, LIANG F, et al. User modeling in search logs via a nonparametric Bayesian approach[C]//WSDM'14:Proceedings of the 7th ACM International Conference on Web Search and Data Mining. New York:ACM, 2014:203-212.
[12] BIAN J, LONG B, LI L, et al. Exploiting user preference for online learning in Web content optimization systems[J]. ACM Transactions on Intelligent Systems and Technology-Special Issue on Linking Social Granularity and Functions, 2014, 5(2):Article No. 33.
[13] ELIDAN G, LOTNER N, FRIEDMAN N, et al. Discovering hidden variables:a structure-based approach[C]//NIPS 2000:Proceedings of the 2000 Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2000:479-485.
[14] 吴蕾,张文生,王珏.基于深度学习框架的隐藏主题变量图模型[J].计算机研究与发展,2015,52(1):191-199.(WU L, ZHANG W H, WANG J. Hidden topic variable graphical model based on learning framework[J]. Journal of Computer Research and Development, 2015, 52(1):191-199.).
[15] GUAN L, ALAM M H, RYU W-J, et al. A phrase-based model to discover hidden factors and hidden topics in recommender systems[C]//BigComp 2016:Proceedings of the International Conference on Big Data and Smart Computing. Washington, DC:IEEE Computer Society, 2016:337-340.
[16] 张宏毅,王立威,陈瑜希.概率图模型研究进展综述[J]. 软件学报,2013,24(11):2476-2497. (ZHANG H Y, WANG L W, CHEN Y X. Research progress of probabilistic graphical models:a survey[J]. Journal of Software, 2013, 24(11):2476-2497.).
[17] HRYCEJ T. Gibbs sampling in Bayesian networks[J]. Artificial Intelligence, 1990, 46(3):351-363.
[18] 岳昆,王朝禄,朱运磊,等.基于概率图模型的互联网广告点击率发现[J].华东师范大学学报(自然科学版),2013(3):15-25. (YUE K, WANG C L, ZHU Y L, et al. Click-through rate prediction of online advertisements based on probabilistic graphical model[J]. Journal of East China Normal University (Natural Science), 2013(3):15-25.).
[19] MovieLens[EB/OL].[2016-03-18]. http://grouplens.org/datasets/movielens/latest/.
[20] CHENG J, BELL D A, LIU W. Learning Bayesian networks from data:an efficient approach based on information theory[J]. Artificial Intelligence, 2002, 137(1/2):43-90.
[21] DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society, Series B (Methodological), 2007, 39(1):1-38.
[22] PEARL J. Evidential reasoning using stochastic simulation of causal models[J]. Artificial Intelligence, 1987, 32(2):245-257.
[23] SHIH T-Y, HOU T-C, JIANG J-D, et al. Dynamically integrating item exposure with rating prediction in collaborative filtering[C]//SIGIR'16:Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM, 2016:813-816.

Construction and inference of latent variable model oriented to user preference discovery

面向用户偏好发现的隐变量模型构建与推理

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	CHEN Hengheng, NI Zhiwei, ZHU Xuhui, JIN Yuanyuan, CHEN Qian. Differential privacy high-dimensional data publishing method via clustering analysis [J]. Journal of Computer Applications, 2021, 41(9): 2578-2585.
[2]	SUN Jianqiang, XU Shaohua. Knowledge reasoning method based on differentiable neural computer and Bayesian network [J]. Journal of Computer Applications, 2021, 41(2): 337-342.
[3]	ZHANG Bang, ZHU Jinxin, XU Zhengyi, LIU Pan, WEI Jianming. Bayesian network-based floor localization algorithm [J]. Journal of Computer Applications, 2019, 39(8): 2468-2474.
[4]	WEN Kai, TAN Xiao. Device-to-device caching algorithm based on user preference and replica threshold [J]. Journal of Computer Applications, 2019, 39(7): 2051-2055.
[5]	YANG Jie, LI Songbin, DENG Haojiang. Steganalysis based on Bayesian network for compressed speech [J]. Journal of Computer Applications, 2018, 38(7): 1967-1973.
[6]	HU Min, CHEN Yuanhui, HUANG Hongcheng. Supernetwork link prediction method based on spatio-temporal relation in location-based social network [J]. Journal of Computer Applications, 2018, 38(6): 1682-1690.
[7]	LU Ling, YANG Wu, LIU Xu, LI Yan. Stance detection method based on entity-emotion evolution belief net [J]. Journal of Computer Applications, 2017, 37(5): 1402-1406.
[8]	MU Tao, CHEN Wei, CHEN Songjian. User classification method based on multiple-layer network traffic analysis [J]. Journal of Computer Applications, 2017, 37(3): 705-710.
[9]	XING Zhiwei, TANG Yunxiao, LUO Qian. Dynamic estimation about service time of flight support based on Bayesian network [J]. Journal of Computer Applications, 2017, 37(1): 299-304.
[10]	ZHANG Meng, NAN Zhihong. Trust network random walk model based on user preferences [J]. Journal of Computer Applications, 2016, 36(12): 3363-3368.
[11]	ZHANG Liping, ZHANG Ruixia, WANG Huan, YAN Sheng. Harmfulness prediction of clone code based on Bayesian network [J]. Journal of Computer Applications, 2016, 36(1): 260-265.
[12]	ZHENG Hui, LI Bing, CHEN Donglin, LIU Pingfeng. Personalized recommendation technique for mobile life services based on location cluster [J]. Journal of Computer Applications, 2015, 35(4): 1148-1153.
[13]	MAO Yingchi, JIE Qing, CHEN Hao. Online abnormal event detection with spatio-temporal relationship in river networks [J]. Journal of Computer Applications, 2015, 35(11): 3106-3111.
[14]	DU Yuanwei, SHI Fangyuan, YANG Na. Construction method for Bayesian network based on Dempster-Shafer/analytic hierarchy process [J]. Journal of Computer Applications, 2015, 35(1): 140-146.
[15]	ZHAO Xuewu LIU Guangliang CHENG Xindang JI Junzhong. Bayesian network structure learning algorithm based on topological order and quantum genetic algorithm [J]. Journal of Computer Applications, 2013, 33(06): 1595-1603.