深度学习在信息推荐系统的应用综述
|
摘要
信息推荐是电子商务等信息系统中最重要的技术之一,深度学习是目前最热门的机器学习算法,研究人员对如何利用深度学习完善信息推荐技术开展了大量工作,但是相应的研究总结较少.文中对深度学习在信息推荐领域的相关研究进行全面回顾,首先阐述了信息推荐的内涵及其存在的主要问题,然后详细介绍国内外学者通过深度学习解决上述问题的方法和策略,最后指出深度学习在信息推荐领域下一步的研究重点.本文的梳理对理清深度学习应用脉络,为后续研究提供参考和未来推荐个性化信息服务的发展具有一定意义.
Information recommendation is one of the most important technologies in information systems such as E-commerce and deep learning is the most popular machine learning algorithm. Researchers have done a lot of work on how to use deep learning to improve the performance of information recommendation system,but the corresponding study summed up less. This paper first reviewed the connotation of information recommendation and its main problem of existence,then introduced the methods and strategies of domestic and foreign scholars to solve the above problems through deep learning. Finally,the further research focus in the field of information recommendation based on deep learning were points out. This paper has a certain significance to clarify the application of the deep learning,to provide reference for the follow-up research and the future development of personalized information services.
Information recommendation is one of the most important technologies in information systems such as E-commerce and deep learning is the most popular machine learning algorithm. Researchers have done a lot of work on how to use deep learning to improve the performance of information recommendation system,but the corresponding study summed up less. This paper first reviewed the connotation of information recommendation and its main problem of existence,then introduced the methods and strategies of domestic and foreign scholars to solve the above problems through deep learning. Finally,the further research focus in the field of information recommendation based on deep learning were points out. This paper has a certain significance to clarify the application of the deep learning,to provide reference for the follow-up research and the future development of personalized information services.
引文
[1]Bao Zeng-hui,Song Yu-qing.Research of collaborative filtering algorithm diversity[J].Wireless Communication Technology,2013,22(3):5-9.
[2]Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[3]Tien J M.Big data:Unleashing information[J].Journal of Systems Science and Systems Engineering,2013,22(2):127-151.
[4]Salakhutdinov R,Hinton G.Deep boltzmann machines[J].Journal of M achine Learning Research,2009,5(2):1967-2006.
[5]Bengio Y,Alain G,Yosinski J.Deep generative stochastic networks trainable by backprop[J].Computer Science,2014,2(45):226-234.
[6]Yi Bao-cai,Wang Wen-tong,Wang Li-chun.Reviewof deep learning[J].Journal of Beijing University of Technology,2015,41(1):48-59.
[7]Salakhutdinov R,Mnih A,Hinton G.Restricted Boltzmann machines for collaborative filtering[C].Proceedings of the 24th International Conference on M achine Learning(ICM L'07),ACM,2007:791-798.
[8]Huang Shan-shan.Research of key problems of collaboratve filtering recommendation algorithms[D].Jinan:Shandong University,2016.
[9]Leng Ya-jun,Lu Qing,Liang Chang-yong.Survey of recommendation based on collaborative filtering[J].Pattern Recognition and Artifical Intelligence,2014,27(8):720-734.
[10]Li Gai,Chen Qiang,Li Lei.Collaborative filtering recommendation algorithm based on rating prediction and ranking prediction[J].Acta Electronica Sinica,2017,45(12):3070-3075.
[11]Zhu Yu-xiao,Lv Lin-yuan.Evaluation metrics for recommender systems[J].Jounrnal of University of Electronic Science and Technology of China,2012,41(2):163-175.
[12]Li Liang,Zhang Hai-ning,Li Zong-bo,et al.Research of collaborative filtering recommendation algorithm fusion user attributes in government purchase[J].Journal of Chongqing University of Technology,2015,29(1):76-81.
[13]Wei Su-yun,Ye Ning,Ji Gen-lin,et al.Collaborative filtering recommendation algorithm based on item category and interest[J].Journal of Nanjing University(Natural Sciences),2013,49(2):142-149.
[14]Gao Rui-bo.Collaborative filtering recommendation algorithm based on kernel matrix decomposition and robust estimation[D].Qinhuangdao:Yanshan University,2016.
[15]Wer J,He J,Chen K,et al.Collaborative filtering and deep learning based recommendation system for cold start items[J].Expert Systems with Applications,2016,69(10):1339-1351.
[16]Koren Y.Collaborative filtering with temporal dynamics[J].Communications of the ACM,2009,53(4):89-97.
[17]Hao Wang,Naiyan Wang D-Y Y.Collaborative deep learning for recommender systems[C].Proceedings of the 21th ACM SIGKDDInternational Conference on Knowledge Discovery and Data M ining,2015:1235-1244.
[18]Slaney M.Web-scale multimedia analysis:does content matter?[J].IEEE Multi Media,2011,18(2):12-15.
[19]Zheng L.A survey and critique of deep learning on recommender systems[D].M IT,2016.
[20]Deng S,Huang L,Xu G,et al.On deep learning for trust-aware recommendations in social networks[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(5):1164-1177.
[21]Kim D,Yu H,Yu H,et al.Convolutional matrix factorization for document context-aware recommendation[C].Proceedings of the7th ACM Conference on Recommender Systems,ACM,2016:233-240.
[22]Dai H,Wang Y,Trivedi R,et al.Recurrent coevolutionary latent feature processes for continuous-time recommendation[C].Proceedings of the 1st Workshop on Deep Learning for Recommender Systems,ACM,2016:29-34.
[23]Wang H,Shi X,Yeung D Y.Relational stacked denoising autoencoder for tag recommendation[C].Proceedings of the 29th Association for the Advance of Artificial Intelligence Conference on Artificial Intelligence,AAAI Press,2015:3052-3058.
[24]Lee K-C.Tumblr blog recommendation with boosted inductive matrix completion categories and subject descriptors[C].Proceedings of the 24th ACM International on Conference on Information and Knowledge M anagement,ACM,2015:203-212.
[25]Sahebi S,Brusilovsky P.It takes two to tango:an exploration of domain pairs for cross-domain collaborative filtering[C].Proceedings of the 9th ACM Conference on Recommender Systems,ACM,2015:131-138.
[26]Roy S,Guntuku S C.Latent factor representations for cold-start video recommendation[C].Proceedings of the 10th ACM Conference on Recommender Systems(Rec Sys'16),ACM,2016:99-106.
[27]Almahairi A,Kastner K,Cho K,et al.Learning distributed representations from reviews for collaborative filtering[C].Proceedings of the 9th ACM Conference on Recommender Systems(Rec Sys'15),ACM,2015:147-154.
[28]Jia X,Wang A,Li X,et al.Multi-modal learning for video recommendation based on mobile application usage[C].Proceedings of2018 IEEE International Conference on Big Data,IEEE,2015:837-842.
[29]Xu Z,Chen C,Lukasiewicz T,et al.Tag-aware personalized recommendation using a deep-semantic similarity model with negative sampling[C].Proceedings of 2016 ACM International on Conference on Information and Knowledge M anagement,ACM,2016:1921-1924.
[30]Chenyi Lei,Dong Liu,Weiping Li,et al.Comparative deep learning of hybrid representations for image recommendations[C].Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR'16),2016:2545-2553.
[31]Strub F,Mary J.Collaborative filtering with stacked denoising auto encoders and sparse inputs[C].Proceedings of 2015 NIPS Workshop on M achine Learning for e Commerce,2015:1-8.
[32]Rawat Y S,Kankanhalli M S.ConTagNet:exploiting user context for image tag recommendation[C].Proceedings of 2016 ACM on M ultimedia Conference,ACM,2016:1102-1106.
[33]Lee H,Ahn Y,Lee H,et al.Quote recommendation in dialogue using deep neural network[C].Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR'16),2016:957-960.
[34]Fu Y,Kawale J,Fu Y.Deep collaborative filtering via marginalized denoising auto-encoder[C].Proceedings of 2015 ACM International on Conference on Information and Knowledge M anagement(CIKM'15).ACM,2015:811-820.
[35]Wakita,Oku K,Kawagoe K.Toward fashion-brand recommendation systems using deep-learning:preliminary analysis[J].International Journal of Knowledge Engineering,2016,2(3):128-131.
[36]Cobington P,Adams J,Sargin E.Deep neural networks for youtube recommendations[C].Proceedings of the 10th ACM Conference on Recommender Systems(Rec Sys'16),2016:191-198.
[37]Zhou J,Albatal R,Gurrin C.Applying visual user interest profiles for recommendation and personalisation[C].Proceedings of 2016International Conference on M ultimedia M odeling,Springer,2016:361-366.
[38]Geng X,Zhang H,Bian J,et al.Learning image and user features for recommendation in social networks[C].Proceedings of 2015IEEE International Conference on Computer Vision(ICCV'15),2015:4274-4282.
[39]Elkahky A.A multi-viewdeep learning approach for cross domain user modeling in recommendation systems[C].Proceedings of the24th International Conference on World Wide Web,Cambridge press,2015:278-288.
[40]Wu Dong-yin,Gui Lin,Chen Zhao,et al.Sentiment analysis based on deep representation learning[J].Journal of Chinese Information Processing,2017,31(1):169-176.
[41]Sun Xiao,Pan Ding,Ren Fu-ji.Facial expression recognition using ROI-KNN deep convolutional neural networks[J].Acta Automatica Sinica,2016,42(6):883-891.
[42]Liu Kai,Zhang Li-min,Sun Yong-wei.RBM optimization based on genetic algorithms[J].M icroelectronics&Computer,2015,32(6):96-100.
[43]Hu Z,Yang Z,Salakhutdinov R,et al.Deep neural networks with massive learned knowledge[C].Proceedings of the 2016 Conference on Empirical M ethods in Natural Language Processing,2016:1670-1679.
[44]GoodfellowI J,Pouget-abadie J,Mirza M,et al.Generative adversarial nets[C].Proceedings of 2014 International Conference on Neural Information Processing Systems,M IT Press,2014:2672-2680.
[45]Kingma D P,Ba J.Adam:a method for stochastic optimization[J].Computer Science,2014,12(8):1169-1180.
[46]Lai H,Pan Y,Liu Y,et al.Simultaneous feature learning and hash coding with deep neural networks[C].Proceedings of 2015 Computer Vision and Pattern Recognition(CVPR'15),IEEE,2015:3270-3278.
[47]Wang J,Song Y,Leung T,et al.Learning fine-grained image similarity with deep ranking[C].Proceedings of 2014 Computer Vision and Pattern Recognition(CVPR'14),IEEE,2014:1386-1393.
[1]包增辉,宋余庆.协同过滤算法的多样性研究[J].无线通信技术,2013,22(3):5-9.
[6]尹宝才,王文通,王立春.深度学习研究综述[J].北京工业大学学报,2015,41(1):48-59.
[8]黄山山.协同过滤推荐算法的关键性问题研究[D].济南:山东大学,2016.
[9]冷亚军,陆青,梁昌勇.协同过滤推荐技术综述[J].模式识别与人工智能,2014,27(8):720-734.
[10]李改,陈强,李磊.基于评分预测与排序预测的协同过滤推荐算法[J].电子学报,2017,45(12):3070-3075.
[11]朱郁筱,吕琳媛.推荐系统评价指标综述[J].电子科技大学学报,2012,41(2):163-175.
[12]李梁,张海宁,李宗博,等.融合用户属性的协同过滤推荐算法在政府采购中的应用[J].重庆理工大学学报,2015,29(1):76-81.
[13]韦素云,业宁,吉根林,等.基于项目类别和兴趣度的协同过滤推荐算法[J].南京大学学报(自然科学),2013,49(2):142-149.
[14]高瑞波.基于核矩阵分解和鲁棒估计的协同过滤推荐算法[D].秦皇岛:燕山大学,2016.
[40]吴冬茵,桂林,陈钊,等.基于深度表示学习和高斯过程迁移学习的情感分析方法[J].中文信息学报,2017,31(1):169-176.
[41]孙晓,潘汀,任福继.基于ROI-KNN卷积神经网络的面部表情识别[J].自动化学报,2016,42(6):883-891.
[42]刘凯,张立民,孙永威.基于遗传算法的RBM优化设计[J].微电子学与计算机,2015,32(6):96-100.
[2]Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[3]Tien J M.Big data:Unleashing information[J].Journal of Systems Science and Systems Engineering,2013,22(2):127-151.
[4]Salakhutdinov R,Hinton G.Deep boltzmann machines[J].Journal of M achine Learning Research,2009,5(2):1967-2006.
[5]Bengio Y,Alain G,Yosinski J.Deep generative stochastic networks trainable by backprop[J].Computer Science,2014,2(45):226-234.
[6]Yi Bao-cai,Wang Wen-tong,Wang Li-chun.Reviewof deep learning[J].Journal of Beijing University of Technology,2015,41(1):48-59.
[7]Salakhutdinov R,Mnih A,Hinton G.Restricted Boltzmann machines for collaborative filtering[C].Proceedings of the 24th International Conference on M achine Learning(ICM L'07),ACM,2007:791-798.
[8]Huang Shan-shan.Research of key problems of collaboratve filtering recommendation algorithms[D].Jinan:Shandong University,2016.
[9]Leng Ya-jun,Lu Qing,Liang Chang-yong.Survey of recommendation based on collaborative filtering[J].Pattern Recognition and Artifical Intelligence,2014,27(8):720-734.
[10]Li Gai,Chen Qiang,Li Lei.Collaborative filtering recommendation algorithm based on rating prediction and ranking prediction[J].Acta Electronica Sinica,2017,45(12):3070-3075.
[11]Zhu Yu-xiao,Lv Lin-yuan.Evaluation metrics for recommender systems[J].Jounrnal of University of Electronic Science and Technology of China,2012,41(2):163-175.
[12]Li Liang,Zhang Hai-ning,Li Zong-bo,et al.Research of collaborative filtering recommendation algorithm fusion user attributes in government purchase[J].Journal of Chongqing University of Technology,2015,29(1):76-81.
[13]Wei Su-yun,Ye Ning,Ji Gen-lin,et al.Collaborative filtering recommendation algorithm based on item category and interest[J].Journal of Nanjing University(Natural Sciences),2013,49(2):142-149.
[14]Gao Rui-bo.Collaborative filtering recommendation algorithm based on kernel matrix decomposition and robust estimation[D].Qinhuangdao:Yanshan University,2016.
[15]Wer J,He J,Chen K,et al.Collaborative filtering and deep learning based recommendation system for cold start items[J].Expert Systems with Applications,2016,69(10):1339-1351.
[16]Koren Y.Collaborative filtering with temporal dynamics[J].Communications of the ACM,2009,53(4):89-97.
[17]Hao Wang,Naiyan Wang D-Y Y.Collaborative deep learning for recommender systems[C].Proceedings of the 21th ACM SIGKDDInternational Conference on Knowledge Discovery and Data M ining,2015:1235-1244.
[18]Slaney M.Web-scale multimedia analysis:does content matter?[J].IEEE Multi Media,2011,18(2):12-15.
[19]Zheng L.A survey and critique of deep learning on recommender systems[D].M IT,2016.
[20]Deng S,Huang L,Xu G,et al.On deep learning for trust-aware recommendations in social networks[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(5):1164-1177.
[21]Kim D,Yu H,Yu H,et al.Convolutional matrix factorization for document context-aware recommendation[C].Proceedings of the7th ACM Conference on Recommender Systems,ACM,2016:233-240.
[22]Dai H,Wang Y,Trivedi R,et al.Recurrent coevolutionary latent feature processes for continuous-time recommendation[C].Proceedings of the 1st Workshop on Deep Learning for Recommender Systems,ACM,2016:29-34.
[23]Wang H,Shi X,Yeung D Y.Relational stacked denoising autoencoder for tag recommendation[C].Proceedings of the 29th Association for the Advance of Artificial Intelligence Conference on Artificial Intelligence,AAAI Press,2015:3052-3058.
[24]Lee K-C.Tumblr blog recommendation with boosted inductive matrix completion categories and subject descriptors[C].Proceedings of the 24th ACM International on Conference on Information and Knowledge M anagement,ACM,2015:203-212.
[25]Sahebi S,Brusilovsky P.It takes two to tango:an exploration of domain pairs for cross-domain collaborative filtering[C].Proceedings of the 9th ACM Conference on Recommender Systems,ACM,2015:131-138.
[26]Roy S,Guntuku S C.Latent factor representations for cold-start video recommendation[C].Proceedings of the 10th ACM Conference on Recommender Systems(Rec Sys'16),ACM,2016:99-106.
[27]Almahairi A,Kastner K,Cho K,et al.Learning distributed representations from reviews for collaborative filtering[C].Proceedings of the 9th ACM Conference on Recommender Systems(Rec Sys'15),ACM,2015:147-154.
[28]Jia X,Wang A,Li X,et al.Multi-modal learning for video recommendation based on mobile application usage[C].Proceedings of2018 IEEE International Conference on Big Data,IEEE,2015:837-842.
[29]Xu Z,Chen C,Lukasiewicz T,et al.Tag-aware personalized recommendation using a deep-semantic similarity model with negative sampling[C].Proceedings of 2016 ACM International on Conference on Information and Knowledge M anagement,ACM,2016:1921-1924.
[30]Chenyi Lei,Dong Liu,Weiping Li,et al.Comparative deep learning of hybrid representations for image recommendations[C].Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR'16),2016:2545-2553.
[31]Strub F,Mary J.Collaborative filtering with stacked denoising auto encoders and sparse inputs[C].Proceedings of 2015 NIPS Workshop on M achine Learning for e Commerce,2015:1-8.
[32]Rawat Y S,Kankanhalli M S.ConTagNet:exploiting user context for image tag recommendation[C].Proceedings of 2016 ACM on M ultimedia Conference,ACM,2016:1102-1106.
[33]Lee H,Ahn Y,Lee H,et al.Quote recommendation in dialogue using deep neural network[C].Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR'16),2016:957-960.
[34]Fu Y,Kawale J,Fu Y.Deep collaborative filtering via marginalized denoising auto-encoder[C].Proceedings of 2015 ACM International on Conference on Information and Knowledge M anagement(CIKM'15).ACM,2015:811-820.
[35]Wakita,Oku K,Kawagoe K.Toward fashion-brand recommendation systems using deep-learning:preliminary analysis[J].International Journal of Knowledge Engineering,2016,2(3):128-131.
[36]Cobington P,Adams J,Sargin E.Deep neural networks for youtube recommendations[C].Proceedings of the 10th ACM Conference on Recommender Systems(Rec Sys'16),2016:191-198.
[37]Zhou J,Albatal R,Gurrin C.Applying visual user interest profiles for recommendation and personalisation[C].Proceedings of 2016International Conference on M ultimedia M odeling,Springer,2016:361-366.
[38]Geng X,Zhang H,Bian J,et al.Learning image and user features for recommendation in social networks[C].Proceedings of 2015IEEE International Conference on Computer Vision(ICCV'15),2015:4274-4282.
[39]Elkahky A.A multi-viewdeep learning approach for cross domain user modeling in recommendation systems[C].Proceedings of the24th International Conference on World Wide Web,Cambridge press,2015:278-288.
[40]Wu Dong-yin,Gui Lin,Chen Zhao,et al.Sentiment analysis based on deep representation learning[J].Journal of Chinese Information Processing,2017,31(1):169-176.
[41]Sun Xiao,Pan Ding,Ren Fu-ji.Facial expression recognition using ROI-KNN deep convolutional neural networks[J].Acta Automatica Sinica,2016,42(6):883-891.
[42]Liu Kai,Zhang Li-min,Sun Yong-wei.RBM optimization based on genetic algorithms[J].M icroelectronics&Computer,2015,32(6):96-100.
[43]Hu Z,Yang Z,Salakhutdinov R,et al.Deep neural networks with massive learned knowledge[C].Proceedings of the 2016 Conference on Empirical M ethods in Natural Language Processing,2016:1670-1679.
[44]GoodfellowI J,Pouget-abadie J,Mirza M,et al.Generative adversarial nets[C].Proceedings of 2014 International Conference on Neural Information Processing Systems,M IT Press,2014:2672-2680.
[45]Kingma D P,Ba J.Adam:a method for stochastic optimization[J].Computer Science,2014,12(8):1169-1180.
[46]Lai H,Pan Y,Liu Y,et al.Simultaneous feature learning and hash coding with deep neural networks[C].Proceedings of 2015 Computer Vision and Pattern Recognition(CVPR'15),IEEE,2015:3270-3278.
[47]Wang J,Song Y,Leung T,et al.Learning fine-grained image similarity with deep ranking[C].Proceedings of 2014 Computer Vision and Pattern Recognition(CVPR'14),IEEE,2014:1386-1393.
[1]包增辉,宋余庆.协同过滤算法的多样性研究[J].无线通信技术,2013,22(3):5-9.
[6]尹宝才,王文通,王立春.深度学习研究综述[J].北京工业大学学报,2015,41(1):48-59.
[8]黄山山.协同过滤推荐算法的关键性问题研究[D].济南:山东大学,2016.
[9]冷亚军,陆青,梁昌勇.协同过滤推荐技术综述[J].模式识别与人工智能,2014,27(8):720-734.
[10]李改,陈强,李磊.基于评分预测与排序预测的协同过滤推荐算法[J].电子学报,2017,45(12):3070-3075.
[11]朱郁筱,吕琳媛.推荐系统评价指标综述[J].电子科技大学学报,2012,41(2):163-175.
[12]李梁,张海宁,李宗博,等.融合用户属性的协同过滤推荐算法在政府采购中的应用[J].重庆理工大学学报,2015,29(1):76-81.
[13]韦素云,业宁,吉根林,等.基于项目类别和兴趣度的协同过滤推荐算法[J].南京大学学报(自然科学),2013,49(2):142-149.
[14]高瑞波.基于核矩阵分解和鲁棒估计的协同过滤推荐算法[D].秦皇岛:燕山大学,2016.
[40]吴冬茵,桂林,陈钊,等.基于深度表示学习和高斯过程迁移学习的情感分析方法[J].中文信息学报,2017,31(1):169-176.
[41]孙晓,潘汀,任福继.基于ROI-KNN卷积神经网络的面部表情识别[J].自动化学报,2016,42(6):883-891.
[42]刘凯,张立民,孙永威.基于遗传算法的RBM优化设计[J].微电子学与计算机,2015,32(6):96-100.