Survey of Graph Neural Networks in Session Recommender Systems

doi:10.3778/j.issn.1002-8331.2207-0397

Abstract

Abstract: Based on the current session of the target user, session recommenders learn the dependency relationship among items according to the auxiliary information such as item category, cross-session context, and user’s multi behaviors, to capture the long-term and short-term preferences of users for personalized recommendations. In recent years, a series of popular algorithms based on deep learning have become the forefront methods for session recommendation systems. The introduction of graph neural networks further improves the session recommendation system’s performance. Given this, the review starts with question definition, session recommendation factors, and composition analysis. Then the related works are divided into session recommendation systems based on graph convolution networks, gated graph neural networks, graph attention networks, and other architectures. After that, these works are summarized and compared. Finally, the categories of loss functions, selected data sets, and model performance evaluation indexes are deeply analyzed. The paper mainly evaluates and sorts out each model framework from algorithm principle and performance analysis, aiming at reviewing, summarizing, and looking into the related work of session recommendation systems based on graph neural networks in the last five years.

Key words: graph neural networks, session recommendation, graph convolution, gated mechanism, attention

摘要： 会话推荐立足于目标用户的当前会话，根据项目类别、跨会话的上下文信息、多种用户行为等辅助信息学习项目间的依赖关系，从而捕捉用户的长短期偏好进行个性化推荐。近年来，流行的深度学习系列方法已经成为会话型推荐系统这个研究热点的前沿方法，尤其是图神经网络的引入，使会话推荐系统的性能得到了进一步提升。鉴于此，该综述从问题定义与会话推荐因素出发，从构图方面进行分析；将相关工作分为基于图卷积网络、门控图神经网络、图注意力网络和其他图神经网络架构的会话推荐系统，并进行归纳与对比；对各工作实验部分中的损失函数类别、所选用的数据集和模型性能评估指标三方面进行深入分析。重点从算法原理和性能分析两方面对各模型框架进行评估和梳理，旨在对近五年基于图神经网络的会话推荐系统相关工作进行评述、总结与展望。

关键词: 图神经网络, 会话推荐, 图卷积, 门控机制, 注意力

ZHU Zhiguo, LI Weiyue, JIANG Pan, ZHOU Peiyao. Survey of Graph Neural Networks in Session Recommender Systems[J]. Computer Engineering and Applications, 2023, 59(5): 55-69.

朱志国, 李伟玥, 姜盼, 周沛瑶. 图神经网络会话推荐系统综述[J]. 计算机工程与应用, 2023, 59(5): 55-69.

References

[1] WU S，SUN F，ZHANG W，et al.Graph neural networks in recommender systems：a survey[J].arXiv：2011.02260，2020.
[2] TANG J，WANG K.Personalized top-n sequential recommendation via convolutional sequence embedding[C]//Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining，2018：565-573.
[3] ZHONG P，WANG D，MIAO C.EEG-based emotion recognition using regularized graph neural networks[J].IEEE Transactions on Affective Computing，2022，13（3）：1290-1301.
[4] MARCHEGGIANI D，BASTINGS J，TITOV I.Exploiting semantics in neural machine translation with graph convolutional networks[J].arXiv：1804.08313，2018.
[5] LUCERI L，ANDREOLETTI D，GIORDANO S.Infringement of tweets geo-location privacy：an approach based on graph convolutional neural networks[J].arXiv：1903. 11206，2019.
[6] QI S，WANG W，JIA B，et al.Learning human-object inter-actions by graph parsing neural networks[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：401-417.
[7] MATSUNAGA D，SUZUMURA T，TAKAHASHI T.Exploring graph neural networks for stock market predictions with rolling window analysis[J].arXiv：1909.10660，2019.
[8] WU S，TANG Y，ZHU Y，et al.Session-based recommendation with graph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：346-353.
[9] ZHANG M，YANG Z.GACOforRec：session-based graph convolutional neural networks recommendation model[J].IEEE Access，2019，7：114077-114085.
[10] SONG W，XIAO Z，WANG Y，et al.Session-based social recommendation via dynamic graph attention networks[C]//Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining，2019：555-563.
[11] 吴国栋，查志康，涂立静，等.图神经网络推荐研究进展[J].智能系统学报，2020，15（1）：14-24.
WU G D，ZHA Z K，TU L J，et al.Research advances in graph neural network recommendation[J].CAAI Transactions on Intelligent Systems，2020，15（1）：14-24.
[12] JANNACH D，LUDEWIG M，LERCHE L.Session-based item recommendation in e-commerce：on short-term intents，reminders，trends and discounts[J].User Modeling and User-Adapted Interaction，2017，27（3）：351-392.
[13] GABRIEL DE SOUZA P M，JANNACH D，DA CUNHA A M.Con-textual hybrid session-based news recommendation with recurrent neural networks[J].IEEE Access，2019，7：169185-169203.
[14] CHEN T，WONG R C W.An efficient and effective framework for session-based social recommendation[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining，2021：400-408.
[15] CHEN J，LI H，ZHANG F，et al.Session-based recommendation with heterogeneous graph neural network[J].arXiv：2108.05641，2021.
[16] YU B，ZHANG R，CHEN W，et al.Graph neural network based model for multi-behavior session-based recommendation[J].GeoInformatica，2021：1-19.
[17] ZHANG C，LIU Q，ZHANG Z.DSGNN：a dynamic and static intentions integrated graph neural network for session-based recommendation[J].Neurocomputing，2022，468：222-232.
[18] SUN Q，ZHANG Z，SANG S，et al.Time and position aware graph neural networks for session-based recommendation[C]//2021 7th International Conference on Computer and Communications（ICCC），2021：1289-1293.
[19] PAN Z，CAI F，CHEN W，et al.Star graph neural networks for session-based recommendation[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management，2020：1195-1204.
[20] XIA X，YIN H，YU J，et al.Self-supervised hypergraph convolutional networks for session-based recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2021，35（5）：4503-4511.
[21] CHEN T，WONG R C W.Handling information loss of graph neural networks for session-based recommendation[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining，2020：1172-1180.
[22] 曹京.基于图神经网络的会话推荐技术研究[D].成都：电子科技大学，2021.
CAO J.Research of session-based recommendation with graph neural network[D].Chengdu：University of Electronic Science and Technology of China，2021.
[23] CHEN Y H，HUANG L，WANG C D，et al.Hybrid-order gated graph neural network for session-based recommendation[J].IEEE Transactions on Industrial Informatics，2021，18（3）：1458-1467.
[24] LI A，CHENG Z，LIU F，et al.Disentangled graph neural networks for session-based recommendation[J].arXiv：2201.03482，2022.
[25] WANG W，ZHANG W，LIU S，et al.Beyond clicks：modeling multi-relational item graph for session-based target behavior prediction[C]//Proceedings of The Web Conference 2020，2020：3056-3062.
[26] ZHENG Y，LIU S，LI Z，et al.DGTN：dual-channel graph transition network for session-based recommendation[C]//2020 International Conference on Data Mining Workshops（ICDMW），2020：236-242.
[27] XIA X，YIN H，YU J，et al.Self-supervised graph co-training for session-based recommendation[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management，2021：2180-2190.
[28] 曹万平，周刚，陈黎，等.基于会话的图卷积递归神经网络推荐模型[J].四川大学学报（自然科学版），2021，58（2）：66-72.
CAO W P，ZHOU G，CHEN L，et al.Session-based graph convolutional recurrent neural networks recommendation model[J].Journal of Sichuan University（Natural Science Edition），2021，58（2）：66-72.
[29] 曹万平.基于图神经网络的会话推荐方法研究[D].成都：四川大学，2021.
CAO W P.Research on session recommendation method based on graph neural networks[D].Chengdu：Sichuan University，2021.
[30] 陈姝.基于图卷积神经网络的会话推荐研究[D].大连：大连理工大学，2021.
CHEN S.Research on session-based recommendation with graph convolutional networks[D].Dalian：Dalian University of Technology，2021.
[31] FENG L，CAI Y，WEI E，et al.Graph neural networks with global noise filtering for session-based recommendation[J].Neurocomputing，2022，472：113-123.
[32] QIU R，YIN H，HUANG Z，et al.GAG：global attributed graph neural network for streaming session-based recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval，2020：669-678.
[33] HUANG C，CHEN J，XIA L，et al.Graph-enhanced multi-task learning of multi-level transition dynamics for session-based recommendation[C]//AAAI Conference on Artificial Intelligence（AAAI），2021.
[34] XU C，ZHAO P，LIU Y，et al.Graph contextualized self-attention network for session-based recommendation[C]//IJCAI，2019：3940-3946.
[35] LU Y，KONG Y，SUN Z，et al.Current interest enhanced graph neural networks for session-based recommendation[C]//2021 26th International Conference on Automation and Computing（ICAC），2021：1-7.
[36] 陈瑶，熊棋，郭一娜.面向会话推荐的注意力图神经网络[J/OL].小型微型计算机系统：1-7[2022-10-27].http：//kns.cnki.net/kcms/detail/21.1106.TP.20211217.1328.007.html
CHEN Y，XIONG Q，GUO Y N.An attention mechanism enhanced graph neural network for session-based recommendation[J/OL].Journal of Chinese Computer Systems：1-7[2022-10-27].http：//kns.cnki.net/kcms/detail/21.1106.TP.20211217.1328.007.html.
[37] YU F，ZHU Y，LIU Q，et al.TAGNN：target attentive graph neural networks for session-based recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval，2020：1921-1924.
[38] WANG B，CAI W.Attention-enhanced graph neural networks for session-based recommendation[J].Mathematics，2020，8（9）：1607.
[39] 孙鑫，刘学军，李斌，等.基于图神经网络和时间注意力的会话序列推荐[J].计算机工程与设计，2020，41（10）：2913-2920.
SUN X，LIU X J，LI B，et al.Graph neural networks with time attention mechanism for session-based re-commendations[J].Computer Engineering and Design，2020，41（10）：2913-2920.
[40] XIAN X，FANG L，SUN S.ReGNN：a repeat aware graph neural network for session-based recommendations[J].IEEE Access，2020，8：98518-98525.
[41] YANG G，ZHANG X，LI Y.Session-based recommendation with graph neural networks for repeat consumption[C]//Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition，2020：519-524.
[42] LIU L，WANG L，LIAN T.CaSe4SR：using category sequence graph to augment session-based recommendation[J].Knowledge-Based Systems，2021，212：106558.
[43] 任俊伟，曾诚，肖丝雨，等.基于会话的多粒度图神经网络推荐模型[J].计算机应用，2021，41（11）：3164-3170.
REN J W，ZENG C，XIAO S Y，et al.Session-based recommendation model of multi-granular graph neural network[J].Journal of Computer Applications，2021，41（11）：3164-3170.
[44] 南宁，杨程屹，武志昊.基于多图神经网络的会话感知推荐模型[J].计算机应用，2021，41（2）：330-336.
NAN N，YANG C Y，WU Z H.Multi-graph neural network-based session perception recommendation model[J].Journal of Computer Applications，2021，41（2）：330-336.
[45] CHEN M，ZHENG J.Incorporating adjacent user modeling into session-based recommendation with graph neural networks[C]//2021 International Conference on Data Mining Workshops（ICDMW），2021：1-9.
[46] SHEN X，YANG C，JIANG Z，et al.Hierarchical graph neural networks for personalized recommendations with user-session context[C]//International Conference on Smart Computing and Communication.Cham：Springer，2019：341-348.
[47] GUO Y，LING Y，CHEN H.A time-aware graph neural network for session-based recommendation[J].IEEE Access，2020，8：167371-167382.
[48] ZHANG C，LI Z，CHEN T，et al.ITGNN：item transition attentive graph neural network for session-based recommendation[C]//Proceedings of the 2021 ACM International Conference on Intelligent Computing and Its Emerging Applications，2021：211-216.
[49] ZHANG M，WU S，GAO M，et al.Personalized graph neural networks with attention mechanism for session-aware recommendation[J].IEEE Transactions on Knowledge and Data Engineering，2022，34（8）：3946-3957.
[50] ZHANG X，ZHOU Y，WANG J，et al.Personal interest attention graph neural networks for session-based recommendation[J].Entropy，2021，23（11）：1500.
[51] GUO W，WANG S，LU W，et al.Sequential dependency enhanced graph neural networks for session-based recommendations[C]//2021 IEEE 8th International Conference on Data Science and Advanced Analytics（DSAA），2021：1-10.
[52] ZHENG J，YU K，GE Z，et al.Session-based query recommendation with graph neural networks on heterogeneous information trees[C]//The International Conference on Natural Computation，Fuzzy Systems and Knowledge Discovery.Cham：Springer，2020：1629-1638.
[53] GUPTA P，GARG D，MALHOTRA P，et al.NISER：normalized item and session representations with graph neural networks[J].arXiv：1909.04276，2019.
[54] ABUGABAH A，CHENG X，WANG J.Dynamic graph attention-aware networks for session-based recommendation[C]//2020 International Joint Conference on Neural Networks（IJCNN），2020：1-7.
[55] GUO J，YANG Y，SONG X，et al.modeling multi-granularity user intent evolving via heterogeneous graph neural networks for session-based recommendation[J].arXiv：2112.13197，2021.
[56] WANG J，DING K，ZHU Z，et al.Session-based recommendation with hypergraph attention networks[C]//Proceedings of the 2021 SIAM International Conference on Data Mining（SDM），2021：82-90.
[57] SHEN Q，WU L，PANG Y，et al.Multi-behavior graph contextual aware network for session-based recommendation[J].arXiv：2109.11903，2021.
[58] CUI C，SHEN Q，ZHU S，et al.Intention adaptive graph neural network for category-aware session-based recommendation[J].arXiv：2112.15352，2021.
[59] WANG Z，WEI W，CONG G，et al.Global context enhanced graph neural networks for session-based recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval，2020：169-178.
[60] GENG C，WU H，FANG H.Causality and correlation graph modeling for effective and explainable session-based recommendation[J].arXiv：2201.10782，2022.
[61] QIU R，LI J，HUANG Z，et al.Rethinking the item order in session-based recommendation with graph neural networks[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management，2019：579-588.
[62] QIU R，HUANG Z，LI J，et al.Exploiting cross-session information for session-based recommendation with graph neural networks[J].ACM Transactions on Information Systems，2020，38（3）：1-23.
[63] ZHANG K，ZHU Y，WANG J，et al.Adaptive structural fingerprints for graph attention networks[C]//International Conference on Learning Representations，2019.
[64] KNYAZEV B，TAYLOR G W，AMER M.Understanding attention and generalization in graph neural networks[C]//Advances in Neural Information Processing Systems，2019.
[65] WANG J，XU Q，LEI J，et al.PA-GGNN：session-based recommendation with position-aware gated graph attention network[C]//2020 IEEE International Conference on Multimedia and Expo（ICME），2020：1-6.
[66] 何倩倩，孙静宇，曾亚竹.基于邻域感知图神经网络的会话推荐[J].计算机工程与应用，2022，58（9）：107-115.
HE Q Q，SUN J Y，ZENG Y Z.Neighborhood awareness graph neural networks for session-based recommendation[J].Computer Engineering and Applications，2022，58（9）：107-115.
[67] PANG Y，WU L，SHEN Q，et al.Heterogeneous global graph neural networks for personalized session-based recommendation[C]//Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining，2022：775-783.
[68] DENG K，HUANG J，QIN J.HybridGNN-SR：combining unsupervised and supervised graph learning for session-based recommendation[C]//2020 International Conference on Data Mining Workshops（ICDMW），2020：136-143.
[69] YAO H，HU J，XIE W，et al.Session-based recommendation model based on multiple neural networks hybrid extraction feature[C]//2020 IEEE International Conference on Big Data（Big Data），2020：5315-5322.
[70] PEROZZI B，AL-RFOU R，SKIENA S.Deepwalk：online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，2014：701-710.
[71] MIKOLOV T，CHEN K，CORRADO G，et al.Efficient estimation of word representations in vector space[J].arXiv：1301.3781，2013.
[72] HU L，CAO L，WANG S，et al.Diversifying personalized recommendation with user-session context[C]//IJCAI，2017：1858-1864.
[73] ZHANG X，XU B，YANG L，et al.Price DOES matter! modeling price and interest preferences in session-based recommendation[J].arXiv：2205.04181，2022.
[74] GUO J，YANG Y，SONG X，et al.Learning multi-granularity consecutive user intent unit for session-based recommendation[C]//Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining，2022：343-352.
[75] REN P，CHEN Z，LI J，et al.RepeatNet：a repeat aware neural recommendation machine for session-based recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：4806-4813.