个性化推荐系统技术进展

doi:10.11896/jsjkx.200200114

摘要/Abstract

摘要： 推荐系统通过获取用户的历史行为数据,如网页的浏览数据、购买记录、社交网络信息、用户地理位置等,来推断用户偏好。随着计算机技术的发展,推荐系统所采用的推荐技术由早期的基于用户-项的数据矩阵分解技术为主,逐渐向与数据挖掘、机器学习、人工智能等技术相融合的方向发展,从而深度挖掘用户行为的潜在偏好,以构建更加精准的用户偏好模型。推荐过程也从静态预测发展到实时推荐,通过与用户实时交互来使推荐结果更加丰富。文中重点回顾了推荐系统在不同时期所采用的关键技术,主要包括基于内容过滤的推荐技术、基于协同过滤的推荐技术、基于深度学习的推荐技术、基于强化学习的推荐技术和基于异构网络的推荐技术等。最后对比和分析了关键技术的优缺点,并对推荐系统的未来发展进行展望。

关键词: 矩阵分解, 强化学习, 神经网络, 推荐算法, 异构信息网络

Abstract: The recommendation system obtains users’ historical behavior data to predict their preferences,such as web browsing data,purchase records,social network information,users’ geographical location and so on.With the development of computer technology,the recommendation technology is mainly based on user-item data matrix decomposition technology in the early stage.Afterwards,it is gradually integrated with data mining,machine learning,artificial intelligence and other technologies,so as to deeply mine the potential preferences of user behavior and build a more accurate user preference model.The recommendation process also moves from static prediction to real-time recommendation,enriching the recommendation results through real-time interaction with users.This paper mainly reviews the key technologies adopted by the recommendation system in different periods,including content-based filtering technology,collaborative filtering technology,recommendation technology based on deep learning,recommendation technology based on reinforcement learning,recommendation technology based on heterogeneous information network.Finally,this paper analyzes the advantages and disadvantages of key technologies,and then looks forward to the future development of the recommendation system.

Key words: Heterogeneous information network, Matrix factorization, Neural network, Recommendation algorithms, Reinforcement learning

中图分类号:

TP311.5

刘君良, 李晓光. 个性化推荐系统技术进展[J]. 计算机科学, 2020, 47(7): 47-55. https://doi.org/10.11896/jsjkx.200200114

LIU Jun-liang, LI Xiao-guang. Techniques for Recommendation System:A Survey[J]. Computer Science, 2020, 47(7): 47-55. https://doi.org/10.11896/jsjkx.200200114

参考文献

[1]YAHYA A M,MD N S,NORWATI M,et al.Improved web page recommender system based on web usage mining [C]//The 3rd International Conference on Computing and Informatics (ICOCI).2011:8-9.
[2]MANJULA W,VIVIEN P,NAOMAL D,et al.Selecting a text similarity measure for a content-based recommender system [J].The Electronic Library,2019,37(3):506-527.
[3]SUN X,XU X L,et al.CROA:A Content-Based Recommendation Optimization Algorithm for Personalized Knowledge Servi-ces[C]//21st International Conference on High Performance Computing and Communications.2019:804-810.
[4] YANIR S,INGRID Z,FABIAN B,et al.Collaborative Inference of Sentiments from Texts [C]//The 18th International Confe-rence.2010:195-206.
[5]AMIT K J,LIU H M,Ingo F,et al.Information Foraging for Enhancing Implicit Feedback in Content-based Image Recommendation[C]//the 11th Forum for Information Retrieval Eva-luation.2019:65-69.
[6]DAVID G,DAVID A N,BRIAN M O,et al.Using coll-aborative filtering to weave an information tapestry [C]//Communications of the ACM.1992:61-70.
[7] PAUL R ,NEOPHYTOS L,MITESH S,et al.GroupLens:an open architecture for collaborative filtering of netnews [C]//ACM 1994 Conference onComputer Supported Cooperative Work.1994:175-186.
[8]BADRUL M,GEORGE K,JOSEPH A,et al.Item-based collaborative filtering recommendation algorithms [C]//The 10th International Conferenceon World Wide Web.2011:285-295.
[9]GREG L,BRENT S,JEREMY Y,et al.Amazon.com Recommendations:Item-to-Item Collaborative Filtering [J].IEEE Internet Computing,2003,7(1):76-80.
[10]YEHUDA K A.Factorization meets then eighborhood:a multifaceted collaborative filtering model [C]//The 14th InternationalConference on Knowledge Discovery and Data Mining.2008:426-434.
[11]DANLEL D L,SEBASTIAN S.Learning the parts of objects by non-negative matrix factorization [C]//Nature.1999:788-791.
[12] PANR,ZHOU Y H,CAO B,et al.One-class collaborative filtering [C]//The 2008 8th IEEE International Conference on Data Mining.2008:1-25.
[13] RUSLAN S,ANDRIY M,et al.Probabilistic Matrix Factorization [C]//Advances in Neural Information Processing Systems 20.2007:1-8.
[14] MA H,IRWIN K,MICHAEL R L,et al.Learning to Recommend with Social Trust Ensemble[C]//International Conference on Research and Development in Information Retrieval.2009:203-210.
[15]WU X Y,CHEN Q M,LIU H,et al.Collaborative FilteringRecommendation Algorithm Based on Representation Learning of Knowledge Graph [J].Computer Engineering,2018,44(2):226-232,263.
[16] DAVID M B,ANDREW Y,et al.Latent Dirichlet Allocation[C]//Journal of Machine Learning Research.2003:993-1022.
[17] CHEN C C,ZHENG X L,WANG Y,et al.Capturing Semantic Correlation for Item Recommendation in Tagging Systems[C]//The 13th AAAI Conference on Artificial Intelligence.2016:108-114.
[18] WANG H,WANG N Y.Collaborative Deep Learning for Recommender Systems [C]//The 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2015:1235-1244.
[19] WANG C,DAVID M B.Collaborative topic modeling for recommending scientific articles [C]//IEEE Transactions on Pattern Analysis Andmachine Intelligence.2011:448-456.
[20]SANJAY P,LIU Y.Collaborative Topic Regression with Social Matrix Factorization for Recommendation Systems [C]//The 29thInternational Conference on Machine Learning.2012:1-8.
[21]AYSUN B,BIRGUL K.HybRecSys:Content-based contextual hybrid venue recommender system[J].Journal of Information Science,2019,45(2):212-226.
[22] VIPUL V,KULKARNI G R.Hybrid Recommender Systems:Survey and Experiments[C]// The 2012 Digital Information and Communication Technology and it’s Applications (DICTAP).2012:469-473.
[23] CHEN X,XU H T,ZHANG Y F,et al.Sequential recommendation with user memory networks [C]//The 11th ACM International Conference on Web Search and Data Mining.2018:108-116.
[24]NIU W,JAMES C,LU H K,et al.Neural Personalized Ranking for Image Recommendation [C]//the 11th ACM International Conference on Web Search and Data Mining.2018:423-431.
[25] BALAZS H,ALEXANDROS K,LINAS B,et al.Session-based recommendations with recurrent neural networks [C]//International Conferenceon Learning Representations.2016:10-15.
[26] YU F,LIU Q,WU S,et al.A dynamic recurrent model for next basket recommendation [C]//The 39th International ACM SIGIR conference on Research and Development in Information Retrieval.2016:729-732.
[27] ZHOU M Z,DING Z Y,TANG J L,et al.Micro Behaviors:A New Perspectivein Ecommerce Recommender Systems [C]//The 11th ACM International Conference on Web Search and Data Mining.2018:727-735.
[28]DUC T L ,HADY W L ,FANG Y.Correlation-Sensitive Next-Basket Recommendation [C]//The 28th International Joint Conference on Artificial Intelligence.2019:2808-2814.
[29] WANG S,SUN L,FAN W,et al.An automated CNN recommendation system for image classification tasks [C]//2017 IEEE International Conference on Multimedia and Expo.2017:283-288.
[30] ZHENG L,VAHID N,PHILIP S Y,et al.Joint deep modeling of users and items using reviews for recommendation [C]//The 11thACMInternational Conference on Web Search and Data Mining.2017:425-434.
[31] MA R F,ZHANG Q,WANG J W,et al.Mention Recommendation for Multimodal Microblog with Cross-attention Memory Network [C]//The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.2018:195-204.
[32]TANG J X ,WANG K.Personalized Top-N Sequential Recommendation via ConvolutionalSequence Embedding [C]//11th ACM International Conference on Web Search and Data Mining.2018:565-573.
[33] LI C L,NIU X C,LUO X Y,et al.A Review-Driven Neural Model for Sequential Recommendation [C]//The 28th International Joint Conference on Artificial Intelligence Main Track.2019:2866-2872.
[34]WANG J,YU L T,ZHANG W N,et al.IRGAH:A Minimax Game for Unifying Generative Information Retrieval Models [C]//The 40th International ACM SIGIR Conference on Research and Development in Information.2017:515-524.
[35] WU Q,LIU Y,MIAO C Y,et al.PD-GAN:Adversarial Learning for Personalized Diversity-Promoting Recommendation [C]//The 28th International Joint Conference on Artificial Intelligence Main track.2019:3870-3876.
[36] WANG L,ZHANG W,HE X F,et al.Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation [C]// 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2019:2447-2456.
[37] ZHAO X Y,XIA L,YIN D W,et al.Model-Based Reinforce-ment Learning for Whole-Chain Recommendations[C]//The 13th ACM International Conference on Web Search and Data Mining.2019:4-8.
[38] ZHAO X Y,ZHANG L,DING Z Y,et al.Recommendationswith Negative Feedback via Pairwise Deep Reinforcement Learning [C]//The 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:1040-1048.
[39] ZOU L X,XIA L,DING Z Y,et al.Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems [C]//The 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2019:2810-2818.
[40] SHI C,LIU J,ZHUANG F Z,et al.Integrating heterogeneous information via ﬁexible regularization framework for recommendation [M].Knowledgeand Information Systems,2016:835-859.
[41] YU X,REN X,SUN Y Z,et al.Personalized entity recommendation:A heterogeneous information network approach [C]//The 7th ACM International Conference on Web Search and Data Mining.2014:283-292.
[42] WANG R R,MA X,JIANG C,et al.Heterogeneous information network-based music recommendation system in mobile networks[J].Computer Communications,2020,150(1):429-437.
[43] WU S,LI H F,LIU L,et al.A Venture Capital Recommendation Algorithm based on Heterogeneous Information Network[J].International Journal of Computers Communications & Control,2020,15(1):1-8.
[44] HU B B,SHI C.Leveraging Meta-pathbased Context for Top-N Recommendation with ANeural Co-Attention Model [C]//The 24th ACMSIGKDD International Conference on Knowledge Discovery & Data Mining.2018:1531-1540.
[45] WANG Z K,LIU H Z,DU Y P,et al.Unified Embedding Model over Heterogeneous Information Network for Personalized Recommendation [C]// The 28th International Joint Conference on Artificial Intelligence.2019:3813-3819.
[46] YANG L Q,EUGENE B,JOSHUA G,et al.OpenRec:A Modular Framework for Extensible and Adaptable Recommendation Algorithms [C]//The 11th ACM Conference on Web Search and Data Mining.2018:664-672.
[47] YI T,ANH T L.Multi-Pointer Co-Attention Networks for Recommendation [C]//The 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:2309-2318.
[48] ZHANG Y,YIN H Z,HUANG Z,et al.Discrete Deep Learning for Fast Content-Aware Recommendation [C]//The 11th ACM International Conferenceon Web Search and Data Mining.2018:717-726.

相关文章 15

[1]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[3]	熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[4]	刘兴光, 周力, 刘琰, 张晓瀛, 谭翔, 魏急波. 基于边缘智能的频谱地图构建与分发方法 Construction and Distribution Method of REM Based on Edge Intelligence 计算机科学, 2022, 49(9): 236-241. https://doi.org/10.11896/jsjkx.220400148
[5]	宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053
[6]	史殿习, 赵琛然, 张耀文, 杨绍武, 张拥军. 基于多智能体强化学习的端到端合作的自适应奖励方法 Adaptive Reward Method for End-to-End Cooperation Based on Multi-agent Reinforcement Learning 计算机科学, 2022, 49(8): 247-256. https://doi.org/10.11896/jsjkx.210700100
[7]	李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[8]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[9]	王润安, 邹兆年. 基于物理操作级模型的查询执行时间预测方法 Query Performance Prediction Based on Physical Operation-level Models 计算机科学, 2022, 49(8): 49-55. https://doi.org/10.11896/jsjkx.210700074
[10]	陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[11]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[12]	袁唯淋, 罗俊仁, 陆丽娜, 陈佳星, 张万鹏, 陈璟. 智能博弈对抗方法:博弈论与强化学习综合视角对比分析 Methods in Adversarial Intelligent Game:A Holistic Comparative Analysis from Perspective of Game Theory and Reinforcement Learning 计算机科学, 2022, 49(8): 191-204. https://doi.org/10.11896/jsjkx.220200174
[13]	檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[14]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[15]	齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed