双向跨域推荐模型
Journal: Advances in Computer and Autonomous Intelligence Research DOI: 10.12238/acair.v3i4.17934
Abstract
用户冷启动问题是推荐系统面临的一大挑战,而跨域推荐是解决用户冷启动问题的有效手段之一。以往的跨域推荐主要依赖于用户特征的单向映射,即从源推荐领域到目标推荐领域或从目标推荐领域到源推荐领域,没有有效地融合用户在两个推荐领域上的信息。为了解决上述问题,提出了一种双向跨域推荐模型(Bidirectional Cross Domain Recommendation Model,Bi-CDRM),该模型通过训练两个用户特征映射网络,分别实现用户特征从源域到目标域和从目标域到源域的映射,以得到粗粒度的用户映射特征；引入相关性计算单元,利用注意力机制对粗粒度的用户映射特征和交互物品特征进行加权,最后使用平均池化得到更细粒度的用户全局特征。这一过程不仅提升了跨域推荐模型的性能,也增强了用户特征映射的可解释性。在Amazon数据集的三个跨域推荐场景下,Bi-CDRM在评分预测任务中,效果相较于对比模型有显著的提升。
Keywords
推荐系统；跨域推荐；用户冷启动；数据挖掘；深度学习
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1]LINDEN G,SMITH B, YORK J. Amazon.com recommendations: item-to-item collaborative filtering[J].IEEE Internet Compu ting,2003,7(1):76-80.
[2]SU M K,LIM E P,ZHU F D.A survey of recommender systems in twitter[C]//Proceedings of the 4th International Conferen ce on Social Informatics (SocInfo’12). Berlin: Springer, 2012:420-433.(Lecture Notes in Computer Science,Vol.7710).
[3]WANG H W,ZHANG F Z,XIE X,et al.DKN: Deep KnowledgeAware Network for News Recommendation[C]//Proceedings of the 2018 World Wide Web Conference (WWW’18).Geneva:ACM,2018:1835-1844.
[4]CHEN C,ZHANG M, ZHANG Y,et al.Efficient heterogeneous collaborative filtering without negative sampling for recommen dation[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020).Palo Alto:AAAI Press,2020:19-26.
[5]TANG J, BELLETTI F,JAIN S,et al. Towards neural mixture recommender for long range dependent user sequences[C]//Proceedings of the 28th World Wide Web Conference (WWW 2019).
Geneva:ACM,2019:1782-1793.
[6]LOPS P,DE GEMMIS M,SEMERARO G.Content-based Recommen der Systems: State of the Art and Trends[M]//LURIE N, SHAFER J.Recommender Systems Handbook.Boston:Springer,2011:73-105.
[7]HUANG X W,SANG J T,YU J,et al.Learning to Learn a Coldstart Sequential Recommender[J].ACM Transactions on Informa tion Systems,2021,1(1):1-26.
[8]ZANG T Z, ZHU Y, LIU H B, et al. A Survey on Cross-domain Recommendation:Taxonomies,Methods,and Future Directions[J].ACM Transactions on Information Systems,2022,41(2):1-39.
[9]SINGH A P,GORDON G J.Relational Learning via Collect ive Matrix Factorization[C]//Proceedings of the 14th ACM SIG KDD International Conference on Knowledge Discovery and Data Mining.Las Vegas:ACM,2008:650-658.
[10]LONI B,SHI Y,LARSON M,et al.Cross-domain Collaborative Filtering with Factorization Machines[C]//Proceedings of the 36th European Conference on IR Research (ECIR 2014).
Berlin: Springer, 2014: 656-661. (Lecture Notes in Computer Science,Vol.8416)
[11]CHEN C,ZHANG M, WANG C Y, et al. An Efficient Adaptive Transfer Neural Network for Social-aware Recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference
on Research and Development in Information Retrieval (SIGIR 2019).Paris:ACM,2019:225-234.
[12]PERERA D,ZIMMERMANN R.Towards Comprehensive Recom mender Systems: Time-aware Unified Recommendations Based on Listwise Ranking of Implicit Cross-network Data[C]//Procee dings of the 34th AAAI Conference on Artificial Intelligence
(AAAI 2020).Palo Alto:AAAI Press,2020:189-197.
[13]ZHU F,CHEN C C,WANG Y,et al.DTCDR: A Framework for Dual -Target Cross-Domain Recommendation[C]//Proceedings of the
28th ACM International Conference on Information and Know ledge Management (CIKM 2019).Beijing: ACM, 2019:1533-1542.
[14]MAN T,SHEN H W,JIN X L,et al.Cross-domain Recommenda tion: An Embedding and Mapping Approach[C]//Proceedings of the 26th International Joint Conference on Artificial Intellig ence (IJCAI 2017).Melbourne:IJCAI,2017:2464-2470.
[15]ZHU F,WANG Y,CHEN C C,et al.A Graphical and Attentional Framework for Dual Target Cross-domain Recommendation[C]//Proceedings of the 29th International Joint Conference on ArtificialIntelligence(IJCAI 2020).Yokohama:IJCAI,2020:3001-3008.
[16]ELKAHKY A M,SONG Y,HE X D. A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems[C]//Proceedings of the 24th International Conference on World Wide Web (WWW 2015).Florence:ACM,2015:278-288.
[17]PO S H,HE X D, GAO J F, et al. Learning Deep Structured Semantic Models for Web Search Using Clickthrough Data[C]//Proceedings of the 22nd ACM International Conference on
Information & Knowledge Management.San Francisco:ACM, 2013:2333-2338.
[18]LI P,TUZHILIN A.DDTCDR: Deep Dual Transfer Cross Dom ain Recommendation[C]//Proceedings of the 19th ACM Internat ional Conference on Web Search and Data Mining (WSDM ’20).
Houston:ACM,2020:331-339.
[19]ZHU Y C,GE K K,ZHUANG F Z,et al.Transfer-Meta Framew ork for Cross-domain Recommendation to Cold-Start Users[C]
//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’
21).Virtual Event:ACM,2021:1813-1817.
[20]ZHU F,CHEN C C,WANG Y,et al.A Deep Framework for Cross-domain and Cross-system Recommendations[C]//Proceedi ngs of the 27th International Joint Conference on Artificial
Intelligence(IJCAI 2018). Stockholm: IJCAI,2018:3711-3717.
[21]ZHU Y C,TANG Z W,LIU Y D,et al.Personalized Transfer of User Preferences for Cross-domain Recommendation[C]//Proce edings of the 15th ACM International Conference on Web Sea rch and Data Mining (WSDM’22).Tempe: ACM, 2022:1507-1515.
[22]BI Y,SONG L Q,YAO M Q,et al.DCDIR: A Deep Cross-domain Recommendation System for Cold Start Users in Insurance Domain[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retri eval(SIGIR 2020).Virtual Event:ACM,2020:1661-1664.
[23]KANG S K,HWANG J,LEE D,et al.Semi-supervised Learni ng for Cross-domain Recommendation to Cold-start Users[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM 2019). Beijing: ACM,2019:1563-1572.
[24]CHENG H, KOC L, HARMSEN J, et al. Wide & deep learning for recommender systems[C]//Proceedings of the 1st Workshop
on Deep Learning for Recommender Systems.Geneva: ACM, 2016.
[25]QU Y,CAO G,ZHOU C,et al.Product-Based Neural Networks for User Response Prediction[C]//Proceedings of the 16th Inte
rnational Conference on Data Mining (ICDM 2016). Barcelona: IEEE,2016.
[26]GUO H F,TANG R M,YE Y,et al.DeepFM: A FactorizationMachine based Neural Network for CTR Prediction[C]//Proceedi ngs of the 26th International Joint Conference on Artificial Intelligence(IJCAI 2017).Melbourne:IJCAI,2017:1725-1731.
[27]WANG X H,PENG Z H,WANG S Z,et al.Cross-domain Recomm endation for Cold-Start Users via Neighborhood Based Feature Mapping[C]//Proceedings of the 23rd International Conference on Database Systems for Advanced Applications (DASFAA 2018).
Gold Coast:Springer,2018:158-165.
[28]FU W J,PENG Z H,WANG S Z,et al.Deeply Fusing Reviews and Contents for Cold Start Users in Cross-domain Recommendation Systems[C]//Proceedings of the 33rd AAAI Conference on Artific ial Intelligence (AAAI 2019). Honolulu: AAAI Press,2019: 94-101.
[29]CHIN J Y,ZHAO K Q,JOTY S,et al.ANR: Aspect-based Neu ral Recommender[C]//Proceedings of the 27th ACM Internatio nal Conference on Information & Knowledge Management.Torino:ACM,2018:147-156.
[2]SU M K,LIM E P,ZHU F D.A survey of recommender systems in twitter[C]//Proceedings of the 4th International Conferen ce on Social Informatics (SocInfo’12). Berlin: Springer, 2012:420-433.(Lecture Notes in Computer Science,Vol.7710).
[3]WANG H W,ZHANG F Z,XIE X,et al.DKN: Deep KnowledgeAware Network for News Recommendation[C]//Proceedings of the 2018 World Wide Web Conference (WWW’18).Geneva:ACM,2018:1835-1844.
[4]CHEN C,ZHANG M, ZHANG Y,et al.Efficient heterogeneous collaborative filtering without negative sampling for recommen dation[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020).Palo Alto:AAAI Press,2020:19-26.
[5]TANG J, BELLETTI F,JAIN S,et al. Towards neural mixture recommender for long range dependent user sequences[C]//Proceedings of the 28th World Wide Web Conference (WWW 2019).
Geneva:ACM,2019:1782-1793.
[6]LOPS P,DE GEMMIS M,SEMERARO G.Content-based Recommen der Systems: State of the Art and Trends[M]//LURIE N, SHAFER J.Recommender Systems Handbook.Boston:Springer,2011:73-105.
[7]HUANG X W,SANG J T,YU J,et al.Learning to Learn a Coldstart Sequential Recommender[J].ACM Transactions on Informa tion Systems,2021,1(1):1-26.
[8]ZANG T Z, ZHU Y, LIU H B, et al. A Survey on Cross-domain Recommendation:Taxonomies,Methods,and Future Directions[J].ACM Transactions on Information Systems,2022,41(2):1-39.
[9]SINGH A P,GORDON G J.Relational Learning via Collect ive Matrix Factorization[C]//Proceedings of the 14th ACM SIG KDD International Conference on Knowledge Discovery and Data Mining.Las Vegas:ACM,2008:650-658.
[10]LONI B,SHI Y,LARSON M,et al.Cross-domain Collaborative Filtering with Factorization Machines[C]//Proceedings of the 36th European Conference on IR Research (ECIR 2014).
Berlin: Springer, 2014: 656-661. (Lecture Notes in Computer Science,Vol.8416)
[11]CHEN C,ZHANG M, WANG C Y, et al. An Efficient Adaptive Transfer Neural Network for Social-aware Recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference
on Research and Development in Information Retrieval (SIGIR 2019).Paris:ACM,2019:225-234.
[12]PERERA D,ZIMMERMANN R.Towards Comprehensive Recom mender Systems: Time-aware Unified Recommendations Based on Listwise Ranking of Implicit Cross-network Data[C]//Procee dings of the 34th AAAI Conference on Artificial Intelligence
(AAAI 2020).Palo Alto:AAAI Press,2020:189-197.
[13]ZHU F,CHEN C C,WANG Y,et al.DTCDR: A Framework for Dual -Target Cross-Domain Recommendation[C]//Proceedings of the
28th ACM International Conference on Information and Know ledge Management (CIKM 2019).Beijing: ACM, 2019:1533-1542.
[14]MAN T,SHEN H W,JIN X L,et al.Cross-domain Recommenda tion: An Embedding and Mapping Approach[C]//Proceedings of the 26th International Joint Conference on Artificial Intellig ence (IJCAI 2017).Melbourne:IJCAI,2017:2464-2470.
[15]ZHU F,WANG Y,CHEN C C,et al.A Graphical and Attentional Framework for Dual Target Cross-domain Recommendation[C]//Proceedings of the 29th International Joint Conference on ArtificialIntelligence(IJCAI 2020).Yokohama:IJCAI,2020:3001-3008.
[16]ELKAHKY A M,SONG Y,HE X D. A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems[C]//Proceedings of the 24th International Conference on World Wide Web (WWW 2015).Florence:ACM,2015:278-288.
[17]PO S H,HE X D, GAO J F, et al. Learning Deep Structured Semantic Models for Web Search Using Clickthrough Data[C]//Proceedings of the 22nd ACM International Conference on
Information & Knowledge Management.San Francisco:ACM, 2013:2333-2338.
[18]LI P,TUZHILIN A.DDTCDR: Deep Dual Transfer Cross Dom ain Recommendation[C]//Proceedings of the 19th ACM Internat ional Conference on Web Search and Data Mining (WSDM ’20).
Houston:ACM,2020:331-339.
[19]ZHU Y C,GE K K,ZHUANG F Z,et al.Transfer-Meta Framew ork for Cross-domain Recommendation to Cold-Start Users[C]
//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’
21).Virtual Event:ACM,2021:1813-1817.
[20]ZHU F,CHEN C C,WANG Y,et al.A Deep Framework for Cross-domain and Cross-system Recommendations[C]//Proceedi ngs of the 27th International Joint Conference on Artificial
Intelligence(IJCAI 2018). Stockholm: IJCAI,2018:3711-3717.
[21]ZHU Y C,TANG Z W,LIU Y D,et al.Personalized Transfer of User Preferences for Cross-domain Recommendation[C]//Proce edings of the 15th ACM International Conference on Web Sea rch and Data Mining (WSDM’22).Tempe: ACM, 2022:1507-1515.
[22]BI Y,SONG L Q,YAO M Q,et al.DCDIR: A Deep Cross-domain Recommendation System for Cold Start Users in Insurance Domain[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retri eval(SIGIR 2020).Virtual Event:ACM,2020:1661-1664.
[23]KANG S K,HWANG J,LEE D,et al.Semi-supervised Learni ng for Cross-domain Recommendation to Cold-start Users[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM 2019). Beijing: ACM,2019:1563-1572.
[24]CHENG H, KOC L, HARMSEN J, et al. Wide & deep learning for recommender systems[C]//Proceedings of the 1st Workshop
on Deep Learning for Recommender Systems.Geneva: ACM, 2016.
[25]QU Y,CAO G,ZHOU C,et al.Product-Based Neural Networks for User Response Prediction[C]//Proceedings of the 16th Inte
rnational Conference on Data Mining (ICDM 2016). Barcelona: IEEE,2016.
[26]GUO H F,TANG R M,YE Y,et al.DeepFM: A FactorizationMachine based Neural Network for CTR Prediction[C]//Proceedi ngs of the 26th International Joint Conference on Artificial Intelligence(IJCAI 2017).Melbourne:IJCAI,2017:1725-1731.
[27]WANG X H,PENG Z H,WANG S Z,et al.Cross-domain Recomm endation for Cold-Start Users via Neighborhood Based Feature Mapping[C]//Proceedings of the 23rd International Conference on Database Systems for Advanced Applications (DASFAA 2018).
Gold Coast:Springer,2018:158-165.
[28]FU W J,PENG Z H,WANG S Z,et al.Deeply Fusing Reviews and Contents for Cold Start Users in Cross-domain Recommendation Systems[C]//Proceedings of the 33rd AAAI Conference on Artific ial Intelligence (AAAI 2019). Honolulu: AAAI Press,2019: 94-101.
[29]CHIN J Y,ZHAO K Q,JOTY S,et al.ANR: Aspect-based Neu ral Recommender[C]//Proceedings of the 27th ACM Internatio nal Conference on Information & Knowledge Management.Torino:ACM,2018:147-156.
Copyright © 2025 郑键珑, 王丹阳
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License