基于微观行为的自适应多注意力会话推荐

doi:10.11896/jsjkx.210900061

计算机科学 ›› 2022, Vol. 49 ›› Issue (11): 117-125.doi: 10.11896/jsjkx.210900061

• 数据库&大数据&数据科学 • 上一篇下一篇

基于微观行为的自适应多注意力会话推荐

乔晶晶¹, 王莉²

1 太原理工大学信息与计算机学院山西晋中 030600
2 太原理工大学大数据学院山西晋中 030600

收稿日期:2021-09-07 修回日期:2021-10-15 出版日期:2022-11-15 发布日期:2022-11-03
通讯作者: 王莉(wangli@tyut.edu.cn)
作者简介:(2389737257@qq.com)
基金资助:
国家自然科学基金(61872260)

Modeling User Micro-Behavior via Adaptive Multi-Attention Network for Session-based Recommendation

QIAO Jing-jing¹, WANG Li²

1 College of Information and Computer,Taiyuan University of Technology,Jinzhong,Shanxi 030600,China
2 College of Data Science,Taiyuan University of Technology,Jinzhong,Shanxi 030600,China

Received:2021-09-07 Revised:2021-10-15 Online:2022-11-15 Published:2022-11-03
About author:QIAO Jing-jing,born in 1993,Ph.D candidate,is a student member of China Computer Federation.Her main research interests include recommendation system and data mining.
WANG Li,born in 1971,Ph.D,professor,is a senior member of China Computer Federation.Her main research interests include big data computation and analysis,knowledge graph and data mining.
Supported by:
National Natural Science Foundation of China(61872260).

摘要/Abstract

摘要： 会话推荐(Session-based Recommendation,SR)旨在根据短期会话信息推荐用户偏好的下一个物品,它不需要用户的配置文件和长期历史信息,具有广阔的应用前景。现有的SR模型通常关注用户点击行为或仅利用某单一类型的行为数据,忽略了用户点击行为的具体语义,如商品浏览、商品收藏、添加到购物车、购买等。这些不同语义的行为被称为微观行为,能够从微观层面反映用户在购物过程中意图的转换以及决策过程,为改善推荐效果提供了有价值的信息。文中提出了一种基于微观行为的自适应多注意力会话推荐模型(Adaptive Multi-Attention Network,AMAN)。首先,将微观行为组成的会话序列建模为异构有向图,然后建立3个组件进行会话推荐:有向图注意力网络(Directed Graph ATtention network,DGAT)从物品级学习物品表征,自适应捕获具有相同微观操作的物品间的关联性;操作级异构图注意力网络(Operation-level Heterogeneous Graph ATtention network,OHGAT)从操作级学习物品表征,自适应捕获具有不同微观操作的物品间的关联性;微观行为协同注意力网络(Micro-Behavior Co-ATtention network,MBCAT)学习微观行为序列表征,自适应捕获不同微观行为序列间的依赖性。在Yoochoose,Taobao14和Taobao15这3个数据集上的实验结果表明,所提方法优于基线模型。

关键词: 会话推荐, 微观行为, 异构有向图, 注意力网络

Abstract: Session-based recommendation (SR) aims to recommend the next item that matches the user’s preferences based on their short-term session information.It does not need user’s profile and long-term historical information and has a broad application prospect.Existing SR models usually focus on user click behavior or only use a single type of behavior data,ignoring the specific semantics of user click behavior,such as browsing,collecting,carting,purchasing,and so on.These behaviors with different semantics are called micro-behavior,which reflects the transformation of user intention and decision-making process in the shopping process from the micro level and will provide valuable information for improving the recommendation effect.Therefore, an adaptive multi-attention network (AMAN) based on user micro-behavior is proposed for session-based recommendation.First,we model the sequence of micro-behavior as heterogeneous directed graph,and then build three components for session-based recommendation.Directed graph attention network (DGAT) learns item representation from the item level and adaptively captures the associations between items with the same micro-operation.Operation-level heterogeneous graph attention network (OHGAT) learns item representation at the operation-level and adaptively captures the associations between items with different micro-ope-ration.Micro-behavior co-attention network (MBCAT) learns the representation of micro-behavior sequences and adaptively captures the dependencies between different micro-behavior sequences.Experimental results on Yoochoose,Taobao14 and Taobao15 datasets show that AMAN outperforms the state-of-the-art baselines.

Key words: Session-based recommendation, Micro-behavior, Heterogeneous directed graph, Attention network

中图分类号:

TP391

乔晶晶, 王莉. 基于微观行为的自适应多注意力会话推荐[J]. 计算机科学, 2022, 49(11): 117-125. https://doi.org/10.11896/jsjkx.210900061

QIAO Jing-jing, WANG Li. Modeling User Micro-Behavior via Adaptive Multi-Attention Network for Session-based Recommendation[J]. Computer Science, 2022, 49(11): 117-125. https://doi.org/10.11896/jsjkx.210900061

参考文献

[1]WANG S,CAO L,WANG Y,et al.A Survey on Session-based Recommender Systems[EB/OL].(2019-02-13) [2020-09-13].https://arxiv.org/abs/1902.04864.
[2]CAO Y,ZHANG W,SONG B,et al.Position-Aware ContextAttention for Session-based Recommendation[J].Neurocompu-ting,2020,376:65-72.
[3]GUO Y,ZHANG D,LING Y,et al.A Joint Neural Network for Session-Aware Recommendation[J].IEEE Access,2020,8:74205-74215.
[4]HIDASI B,KARATZOGLOU A,BALTRUNAS L,et al.Session-based Recommendations with Recurrent Neural Networks[EB/OL].(2016-03-29) [2020-09-29].https://arxiv.org/abs/1511.06939.
[5]LI J,REN P,CHEN Z,et al.Neural Attentive Session-basedRecommendation[C]//Proceedings of the 26th ACM on Confe-rence on Information and Knowledge Management.ACM,2017:1419-1428.
[6]LIU Q,ZENG Y,MOKHOSI R,et al.STAMP:Short-Term Attention/Memory Priority Model for Session-based Recommendation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2018:1831-1839.
[7]WU S,TANG Y,ZHU Y,et al.Session-based Recommendation with Graph Neural Networks[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence.AAAI,2019:346-353.
[8]XU C,ZHAO P,LIU Y,et al.Graph Contextualized Self-attention Network for Session-based Recommendation[C]//Procee-dings of the 27th International Joint Conference on Artificial Intelligence.AAAI,2018:3940-3946.
[9]WANG W,ZHANG W,LIU S,et al.Beyond Clicks:ModelingMulti-Relational Item Graph for Session-Based Target Behavior Prediction[C]//Proceedings of the 2020 World Wide Web Conference.ACM,2020:3056-3062.
[10]MENG W,YANG D,XIAO Y.Incorporating User Micro-beha-viors and Item Knowledge into Multi-task Learning for Session-based Recommendation[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2020:1091-1100.
[11]SARWAR B,KARYPIS G,KONSTAN J,et al.Item-based Collaborative Filtering Recommendation Algorithms[C]//Procee-dings of the 10th International Conference on World Wide Web.ACM,2001:285-295.
[12]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.BPR:Bayesian Personalized Ranking from Implicit Feedback[C]//Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence.ACM,2009:452-461.
[13]RENDLE S,FREUDENTHALER C,SCHMIDT-THIEME L.Factorizing Personalized Markov Chains for Next-basket Re-commendation[C]//Proceedings of the 19th International Conference on World Wide Web.ACM,2010:811-820.
[14]TAN Y,XU X,LIU Y.Improved Recurrent Neural Networksfor Session-based Recommendations[C]//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems.ACM,2016:17-22.
[15]JANNACH D,LUDEWIG M.When Recurrent Neural Net-works Meet the Neighborhood for Session-Based Recommendation[C]//Proceedings of the 11th ACM Conference on Recommender Systems.ACM,2017:306-310.
[16]HIDASI B,KARATZOGLOU A.Recurrent Neural Networkswith Top-k Gains for Session-based Recommendations[C]//Proceedings of the 27th ACM on Conference on Information and Knowledge Management.ACM,2018:843-852.
[17]LI Z,ZHAO H,LIU Q,et al.Learning from History and Pre-sent:Next-item Recommendation via Discriminatively Exploiting User Behaviors[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2018:1734-1743.
[18]SONG Y,LEE J.Augmenting Recurrent Neural Networks with High-Order User-Contextual Preference for Session-Based Re-commendation [EB/OL].(2018-05-08) [2020-09-13].https://arxiv.org/abs/1805.02983.
[19]CUI Q,WU S,LIU Q,et al.MV-RNN:A Multi-View Recurrent Neural Network for Sequential Recommendation [J].IEEE Transactions on Knowledge and Data Engineering,2020,32:317-331.
[20]QIU R,LI J,HUANG Z,et al.Rethinking the Item Order inSession-based Recommendation with Graph Neural Networks[C]//Proceedings of the 28th ACM on Conference on Information and Knowledge Management.ACM,2019:579-588.
[21]LIU L,WANG L,LIAN T.CaSe4SR:Using Category Sequence Graph to Augment Session-based Recommendation[J/OL].Knowledge-Based Systems,2021,212.https://www.researchgate.net/publication/346770323_CaSe4SR_Using_category_sequence_graph_to_augment_session-based_recommendation.
[22]LE D,LAUW H,FANG Y.Modeling Contemporaneous Basket Sequences with Twin Networks for Next-Item Recommendation[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence.AAAI,2018:3414-3420.
[23]VELICKOVIC P,CUCURULL G,CASANOVA A,et al.Graph Attention Networks [EB/OL].(2018-02-04) [2020-09-13].https://arxiv.org/abs/1710.10903.
[24]CHEN W,CAI F,CHEN H,et al A Dynamic Co-attention Network for Session-based Recommendation[C]//Proceedings of the 28th ACM on Conference on Information and Knowledge Management.ACM,2019:1461-1470.
[25]LUDEWIG M,MAURO N,LATIFI S,et al.Empirical Analysis of Session-Based Recommendation Algorithms [J].User Mode-ling and User-adapted Interaction,2021,31:149-181.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于微观行为的自适应多注意力会话推荐

Modeling User Micro-Behavior via Adaptive Multi-Attention Network for Session-based Recommendation

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

Metrics

本文评价

推荐阅读 0

[1]	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
[2]	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
[3]	蒲岍岍, 雷航, 李贞昊, 李晓瑜. 增强列表信息和用户兴趣的个性化新闻推荐算法 Personalized News Recommendation Algorithm with Enhanced List Information and User Interests 计算机科学, 2022, 49(6): 142-148. https://doi.org/10.11896/jsjkx.210400173
[4]	富坤, 郭云朋, 禚佳明, 李佳宁, 刘琪. 语义增强的完全不平衡标签网络表示学习算法 Semantic Information Enhanced Network Embedding with Completely Imbalanced Labels 计算机科学, 2022, 49(11): 109-116. https://doi.org/10.11896/jsjkx.210900101
[5]	曾伟良, 陈漪皓, 姚若愚, 廖睿翔, 孙为军. 时空图注意力网络在交叉口车辆轨迹预测的应用 Application of Spatial-Temporal Graph Attention Networks in Trajectory Prediction for Vehicles at Intersections 计算机科学, 2021, 48(6A): 334-341. https://doi.org/10.11896/jsjkx.200800066
[6]	杜少华, 万怀宇, 武志昊, 林友芳. 融合文本序列和图信息的海关商品HS编码分类 Customs Commodity HS Code Classification Integrating Text Sequence and Graph Information 计算机科学, 2021, 48(4): 97-103. https://doi.org/10.11896/jsjkx.200900053
[7]	刘志鑫, 张泽华, 张杰. 基于多层次多视角的图注意力Top-N推荐方法 Top-N Recommendation Method for Graph Attention Based on Multi-level and Multi-view 计算机科学, 2021, 48(4): 104-110. https://doi.org/10.11896/jsjkx.200800027
[8]	程昊熠, 李培峰, 朱巧明. 基于注意力机制的事件同指消解方法 Event Coreference Resolution Method Based on Attention Mechanism 计算机科学, 2019, 46(9): 201-205. https://doi.org/10.11896/j.issn.1002-137X.2019.09.029
[9]	贾宁, 郑纯军. 基于LSTM-DA神经网络的农产品价格指数短期预测模型 Short-term Forecasting Model of Agricultural Product Price Index Based onLSTM-DA Neural Network 计算机科学, 2019, 46(11A): 62-65.