基于深度学习的内容推荐算法研究综述

doi:10.19678/j.issn.1000-3428.0060557

摘要/Abstract

摘要： 推荐系统是学习用户偏好，实现个性化推荐的系统化应用技术，在商品购买、影音推荐、关联阅读等多领域得到了广泛的应用。近年来，随着多源异构数据的激增和深度学习的兴起，传统推荐算法中的表征学习模式逐步被深度学习代替。梳理推荐算法的背景和发展趋势，并给出内容推荐的算法思路及其优劣评价，分别介绍多层感知机、自动编码器、卷积神经网络以及循环神经网络等深度学习方法的网络结构和算法优势。从技术应用的视角综述深度学习在内容推荐中的应用现状与研究成果，对不同经典深度推荐算法进行分析与比较。在此基础上，指出深度学习在可解释性、学习效率等方面的不足，并对交叉领域学习、多任务学习、表征学习等未来研究方向进行展望。

关键词: 推荐系统, 表征学习, 内容推荐, 深度学习, 多源异构

Abstract: Recommendation System(RS) is a systematic application technology that learns user preferences to realize personalized recommendation.It has been widely used in commodity purchase,audio and video recommendation,and associated reading.In recent years,the representation learning mode in traditional recommendation algorithms has been gradually replaced by deep learning along with the proliferation of multi-source heterogeneous data and the rise of deep learning.This paper describes the background and development of the recommendation algorithms,discussing the basic ideas of the algorithms,as well as their advantages and disadvantages.The paper particularly focuses on the deep learning-based methods,introducing their merits and network structures,including the multilayer perceptron,auto-encoder,convolutional neural network and recurrent neural network.Then the paper summarizes the application of deep learning in content recommendation and the findings of relevant studies,analyzing and comparing the classical deep recommendation algorithms.On this basis,the shortcomings of deep learning in terms of interpretability and learning efficiency are pointed out,and the future research directions in cross-domain learning,multi-task learning and representation learning are discussed.

Key words: Recommendation System(RS), representation learning, content recommendation, deep learning, multi-source heterogeneity

中图分类号:

TP181

刘华玲, 马俊, 张国祥. 基于深度学习的内容推荐算法研究综述[J]. 计算机工程, 2021, 47(7): 1-12.

LIU Hualing, MA Jun, ZHANG Guoxiang. Review of Studies on Deep Learning-Based Content Recommendation Algorithms[J]. Computer Engineering, 2021, 47(7): 1-12.

http://www.ecice06.com/CN/Y2021/V47/I7/1

图/表 9

20210720202509

20210720202514

20210720202518

20210720202522

20210720202526

20210720202530

20210720202533

20210720202537

20210720202541

参考文献

[1] MARZ N,WARREN J.Big data:principles and best practices of scalable real-time data systems[M].New York,USA:Manning Publications Co.,2015.
[2] 刘青文.基于协同过滤的推荐算法研究[D].合肥:中国科学技术大学,2013. LIU Q W.Research on recommendation algorithm based on collaborative filtering[D].Hefei:University of Science and Technology of China,2013.(in Chinese)
[3] GOLDBERG D,NICHOLS D,OKI B M,et al.Using collaborative filtering to weave an information tapestry[J].Communications of the ACM,1992,35(12):61-70.
[4] RESNICK P,VARIAN H R.Recommender systems[J].Communications of the ACM,1997,40(3):56-58.
[5] MAHMOOD T,RICCI F.Improving recommender systems with adaptive conversational strategies[C]//Proceedings of the 20th ACM Conference on Hypertext and Hypermedia.New York,USA:ACM Press,2009:73-82.
[6] BURKE R.Hybrid Web recommender systems[M].Berlin,Germany:Springer,2007.
[7] 朱扬勇,孙婧.推荐系统研究进展[J].计算机科学与探索,2015,9(5):513-525. ZHU Y Y,SUN J.Research progress of recommender system[J].Computer Science and Exploration,2015,9(5):513-525.(in Chinese)
[8] LINDEN G,SMITH B,YORK J.Amazon.com recommendations:item-to-item collaborative filtering[J].IEEE Internet Computing,2003,7(1):76-80.
[9] CHENG H T,KOC L,HARMSEN J,et al.Wide and deep learning for recommender systems[C]//Proceedings of the 1st IEEE Workshop on Deep Learning for Recommender Systems.Washington D.C.,USA:IEEE Press,2016:7-10.
[10] WANG H,WANG N,YEUNG D Y.Collaborative deep learning for recommender systems[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2015:1235-1244.
[11] SEDHAIN S,MENON A K,SANNER S,et al.Autorec:autoencoders meet collaborative filtering[C]//Proceedings of the 24th IEEE International Conference on World Wide Web.Washington D.C.,USA:IEEE Press,2015:111-112.
[12] COVINGTON P,ADAMS J,SARGIN E.Deep neural networks for youtube recommendations[C]//Proceedings of the 10th ACM Conference on Recommender Systems.New York,USA:ACM Press,2016:191-198.
[13] SCHUTH A,OOSTERHUIS H,WHITESON S,et al.Multileave gradient descent for fast online learning to rank[C]//Proceedings of the 9th ACM International Conference on Web Search and Data Mining.New York,USA:ACM Press,2016:457-466.
[14] LI C,FENG H Y,DE RIJKE M.Cascading hybrid bandits:online learning to rank for relevance and diversity[EB/OL].[2020-12-10].https://arxiv.org/abs/1912.00508.
[15] ADOMAVICIUS G,TUZHILIN A.Toward the next generation of recommender systems:a survey of the state-of-the-art and possible extensions[J].IEEE Transactions on Knowledge and Data Engineering,2005,17(6):734-749.
[16] BURKE R.Hybrid recommender systems:survey and experiments[J].User Modeling and User-Adapted Interaction,2002,12(4):331-370.
[17] JANNACH D,ZANKER M,FELFERNIG A,et al.Recommender systems:an introduction[M].[S.1.]:Cambridge University Press,2010.
[18] BAEZA-YATES R,RIBEIRO-NETO B.Modern information retrieval[M].New York,USA:ACM Press,1999.
[19] PAZZANI M J,BILLSUS D.Content-based recommendation systems[M].Berlin,Germany:Springer,2007.
[20] RENDLE S,KRICHENE W,ZHANG L,et al.Neural collaborative filtering vs.matrix factorization revisited[EB/OL].[2020-12-10].https://arxiv.org/abs/2005.09683.
[21] XU Y,ZHU N.Hybrid recommendation algorithm based on long-term and short-term interest and matrix factorization for collaborative filtering[C]//Proceedings of JPCS'20.[S.l.]:IOP Publishing,2020:16-24.
[22] 冯晨娇,梁吉业,宋鹏,等.基于极端评分行为的相似度计算[J].计算机科学,2020,47(2):31-36. FENG C J,LIANG J Y,SONG P,et al.Similarity calculation based on extreme scoring behavior[J].Computer Science,2020,47(2):31-36.(in Chinese)
[23] DENG L,YU D.Deep learning:methods and applications[J].Foundations and Trends in Signal Processing,2014,7(3/4):197-387.
[24] GOODFELLOW I,BENGIO Y,COURVILLE A,et al.Deep learning[M].Cambridge,USA:MIT Press,2016.
[25] BILLSUSE D,PAZZANI M J.Learning collaborative information filters[C]//Proceedings of IEEE ICML'98.Washington D.C.,USA:IEEE Press,1998:46-54.
[26] 王金辉.基于标签的协同过滤稀疏性问题研究[D].合肥:中国科学技术大学,2011. WANG J H.Research on sparsity of label-based collaborative filtering[D].Hefei:University of Science and Technology of China,2011.(in Chinese)
[27] SCHEIN A I,POPESCUL A,UNGAR L H,et al.Methods and metrics for cold-start recommendations[C]//Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2002:253-260.
[28] 吴焕,王晓箴,潘林,等.基于LINQ的多源异构数据查询中间件[J].计算机工程,2011,37(2):1-3. WU H,WANG X J,BAN L,et al.Multi-source heterogeneous data query middleware based on LINQ[J]. Computer Engineering,2011,37(2):1-3.(in Chinese)
[29] ZHENG L,NOROOZI V,YU P S.Joint deep modeling of users and items using reviews for recommendation[C]//Proceedings of the 20th ACM International Conference on Web Search and Data Mining.New York,USA:ACM Press,2017:425-434.
[30] HE X,LIAO L,ZHANG H,et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web.Perth,Australia:[s.n.],2017:173-182.
[31] HORNIK K.Approximation capabilities of multilayer feedforward networks[J].Neural Networks,1991,4(2):251-257.
[32] HORNIK K,STINCHCOMBE M,WHITE H.Multilayer feedforward networks are universal approximators[J].Neural Networks,1989,2(5):359-366.
[33] CHEN M,XU Z,WEINBERGER K,et al.Marginalized denoising autoencoders for domain adaptation[EB/OL].[2020-12-10].https://arxiv.org/ftp/arxiv/papers/1206/1206.4683.pdf.
[34] LECUN Y,BOSER B,DENKER J S,et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation,1989,1(4):541-551.
[35] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[36] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[37] HE X,CHUA T S.Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2017:355-364.
[38] GUO H F,TANG R M,YE Y M,et al.DeepFM:a factorization-machine based neural network for CTR prediction[EB/OL].[2020-12-10].https://arxiv.org/abs/1703.04247.
[39] CHEN C,ZHAO P,LI L,et al.Locally connected deep learning framework for industrial-scale recommender systems[C]//Proceedings of the 26th IEEE International Conference on World Wide Web Companion.Washington D.C.,USA:IEEE Press,2017:769-770.
[40] ALASHKAR T,JIANG S,WANG S,et al.Examples-rules guided deep neural network for makeup recommendation[C]//Proceedings of AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2017:941-947.
[41] ZHANG W,DU T,WANG J.Deep learning over multi-field categorical data[C]//Proceedings of European Conference on Information Retrieval.Berlin,Germany:Springer,2016:45-57.
[42] QU Y R,CAI H,REN K,et al.Product-based neural networks for user response prediction[EB/OL].[2020-12-10].https://arxiv.org/abs/1611.00144.
[43] LIAN J,ZHOU X,ZHANG F,et al.xDeepFM:combining explicit and implicit feature interactions for recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York,USA:ACM Press,2018:1754-1763.
[44] ELKAHKY A M,SONG Y,HE X.A multi-view deep learning approach for cross domain user modeling in recommendation systems[C]//Proceedings of the 24th IEEE International Conference on World Wide Web.Washington D.C.,USA:IEEE Press,2015:278-288.
[45] ZHANG F,YUAN N J,LIAN D,et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2016:353-362.
[46] NGUYEN P,TOMEO P,DI NOIA T,et al.An evaluation of SimRank and personalized PageRank to build a recommender system for the web of data[C]//Proceedings of the 24th IEEE International Conference on World Wide Web.Washington D.C.,USA:IEEE Press,2015:1477-1482.
[47] YU X,REN X,SUN Y,et al.Personalized entity recommendation:a heterogeneous information network approach[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining.New York,USA:ACM Press,2014:283-292.
[48] WANG C,BLEI D M.Collaborative topic modeling for recommending scientific articles[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2011:448-456.
[49] HE R N,MCAULEY J.VBPR:visual Bayesian personalized ranking from implicit feedback[EB/OL].[2020-12-10].https://arxiv.org/abs/1510.01784.
[50] CATHERINE R,COHEN W.TransNets:learning to transform for recommendation[C]//Proceedings of the 11th ACM Conference on Recommender Systems.New York,USA:ACM Press,2017:288-296.
[51] KIM D,PARK C,OH J,et al.Convolutional matrix factorization for document context-aware recommendation[C]//Proceedings of the 10th ACM Conference on Recommender Systems.New York,USA:ACM Press,2016:233-240.
[52] ZHANG Q,WANG J,HUANG H,et al.Hashtag recommendation for multimodal Microblog using co-attention network[C]//Proceedings of the 23rd International Joint Conference on Artificial Intelligence.Washington D.C.,USA:IEEE Press,2017:3420-3426.
[53] ROSEWELT L A,RENJIT J A.A content recommendation system for effective e-learning using embedded feature selection and fuzzy DT based CNN[J].Journal of Intelligent and Fuzzy Systems,2020,39(8):1-14.
[54] DAI H,WANG Y,TRIVEDI R,et al.Recurrent coevolutionary latent feature processes for continuous-time recommendation[C]//Proceedings of the 1st IEEE Workshop on Deep Learning for Recommender Systems.Washington D.C.,USA:IEEE Press,2016:29-34.
[55] WU C Y,AHMED A,BEUTEL A,et al.Recurrent recommender networks[C]//Proceedings of the 10th ACM International Conference on Web Search and Data Mining.New York,USA:ACM Press,2017:495-503.
[56] CHO K,VAN MERRIENBOER B,BAHDANAU D,et al.On the properties of neural machine translation:encoder-decoder approaches[EB/OL].[2020-12-10].https://arxivarxiv:1409.1259.
[57] BANSAL T,BELANGER D,MCCALLUM A.Ask the GRU:multi-task learning for deep text recommendations[C]//Proceedings of the 10th ACM Conference on Recommender Systems.New York,USA:ACM Press,2016:107-114.
[58] LI P,WANG Z,REN Z,et al.Neural rating regression with abstractive tips generation for recommendation[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2017:345-354.
[59] CHEN Z,WANG X,XIE X,et al.Co-attentive multi-task learning for explainable recommendation[C]//Proceedings of IEEE IJCAI'19.Washington D.C.,USA:IEEE Press,2019:2137-2143.
[60] TANG H,LIU J,ZHAO M,et al.Progressive Layered Extraction(PLE):a novel multi-task learning model for personalized recommendations[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:269-278.
[61] HANSEN C,HANSEN C,MAYSTRE L,et al.Contextual and sequential user embeddings for large-scale music recommendation[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:53-62.
[62] SI P.Approximate nearest neighbour search with the fukunaga & narendra algorithm[D].Barcelona,Spain:Polytechnic University of Catalonia,2011.
[63] ZHOU J P,CHENG Z,PEREZ F,et al.TAFA:two-headed attention fused autoencoder for context-aware recommendations[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:338-347.
[64] WU G,VOLKOVS M,SOON C L,et al.Noise contrastive estimation for one-class collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2019:135-144.
[65] WU Y,DUBOIS C,ZHENG A X,et al.Collaborative denoising auto-encoders for top-n recommender systems[C]//Proceedings of the 9th ACM International Conference on Web Search and Data Mining.New York,USA:ACM Press,2016:153-162.
[66] LIANG D,KRISHNAN R G,HOFFMAN M D,et al.Variational autoencoders for collaborative filtering[C]//Proceedings of 2018 IEEE World Wide Web Conference.Washington D.C.,USA:IEEE Press,2018:689-698.
[67] WANG H,ZHAO Q,WU Q,et al.Global and local differential privacy for collaborative bandits[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:150-159.
[68] TANG J,WEN H,WANG K.Revisiting adversarially learned injection attacks against recommender systems[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:318-327.
[69] PATRO G K,CHAKRABORTY A,BANERJEE A,et al.Towards safety and sustainability:designing local recommendations for post-pandemic world[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:358-367.
[70] ZHANG Y,AI Q,CHEN X,et al.Joint representation learning for top-n recommendation with heterogeneous information sources[C]//Proceedings of 2017 ACM Conference on Information and Knowledge Management.New York,USA:ACM Press,2017:1449-1458.
[71] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[EB/OL].[2020-12-10]. https://arxiv.org/abs/1706.03762.
[72] SEO S,HUANG J,YANG H,et al.Interpretable convolutional neural networks with dual local and global attention for review rating prediction[C]//Proceedings of the 11th ACM Conference on Recommender Systems.New York,USA:ACM Press,2017:297-305.
[73] TAY Y,LUU A T,HUI S C.Multi-pointer co-attention networks for recommendation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York,USA:ACM Press,2018:2309-2318.
[74] HU B,SHI C,ZHAO W X,et al.Leveraging meta-path based context for top-n recommendation with a neural co-attention model[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York,USA:ACM Press,2018:1531-1540.
[75] KHAN M M,IBRAHIM R,GHANI I.Cross domain recommender systems:a systematic literature review[J].ACM Computing Surveys,2017,50(3):1-34.
[76] FERNáNDEZ-TOBíAS I,CANTADOR I,KAMINSKAS M,et al.Cross-domain recommender systems:a survey of the state of the art[EB/OL].[2020-12-10].https://www.researchgate.net/publication/267227272.
[77] PAN W,XIANG E W,LIU N N,et al.Transfer learning in collaborative filtering for sparsity reduction[C]//Proceedings of the 24th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press:2010:230-235.
[78] PEREIRA B L,UEDA A,PENHA G,et al.Online learning to rank for sequential music recommendation[C]//Proceedings of the 13th ACM Conference on Recommender Systems.New York,USA:ACM Press,2019:237-245.
[79] COLLOBERT R,WESTON J.A unified architecture for natural language processing:deep neural networks with multitask learning[C]//Proceedings of the 25th IEEE International Conference on Machine Learning.Washington D.C.,USA:IEEE Press,2008:160-167.
[80] SUTTON R S,BARTO A G.Reinforcement learning:an introduction[M].Cambridge,USA:MIT Press,2018.
[81] YANG L,LIU B,LIN L,et al.Exploring clustering of bandits for online recommendation system[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:120-129.
[82] SANTANA M R O,MELO L C,CAMARGO F H F,et al.Contextual meta-bandit for recommender systems selection[C]//Proceedings of the 14th ACM Conference on Recommender Systems.New York,USA:ACM Press,2020:444-449.
[83] NAJAFABADI M M,VILLANUSTRE F,KHOSHGOFTAAR T M,et al.Deep learning applications and challenges in big data analytics[J].Journal of Big Data,2015,2(1):1-21.

选择文件类型/文献管理软件名称

选择包含的内容