计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231100047-9.doi: 10.11896/jsjkx.231100047

• 大数据&数据科学 • 上一篇    下一篇

MB-ATMK:融合属性权重和时序元知识的多行为序列推荐模型

陈毓哲, 曹琼, 黄贤英, 邹世豪   

  1. 重庆理工大学计算机科学与工程学院 重庆 400054
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 曹琼(jing5589@163.com)
  • 作者简介:(chenyuzhe5233@163.com)
  • 基金资助:
    国家自然科学基金(62141201);重庆市自然科学基金(CSTB2022NSCQ-MSX1672)

MB-ATMK:Multi-behavior Sequential Recommendation Integrating Attribute Weights andTemporal Meta-knowledge

CHEN Yuzhe, CAO Qiong, HUANG Xianying, ZOU Shihao   

  1. College of Computer Science and Engineering,Chongqing University of Technology,Chongqing 400054,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:CHEN Yuzhe,born in 1999,master.His main research interetes include recommendation system and so on.
    CAO Qiong,born in 1979,master,lecturer.Her main research interetes include data science and deep learning.
  • Supported by:
    National Natural Science Foundation of China(62141201) and Natural Science Foundation of Chongqing,China(CSTB2022NSCQ-MSX1672).

PDF (PC)

149

摘要： 序列推荐根据用户和项目的交互序列预测用户未来的偏好,然而现有的方法忽略了在现实场景中用户的多行为交互(如浏览、收藏、加入购物车)。其次,用户的偏好有着时序依赖性,同时也受到属性信息的影响。最后,在多行为序列推荐场景中用户的多行为交互存在复杂依赖关系。因此我们提出了一种融合属性权重和时序元知识的多行为序列推荐模型(MB-ATMK)。首先加入用户的多行为交互数据,并基于用户交互的时间戳设计了时序感知编码模块,通过时序感知注意力捕获了用户的动态偏好。其次引入了用户端和项目端丰富的属性信息,设计了属性权重增强的元知识图神经网络。使用元知识提炼了用户的多偏好模式,并基于图神经网络设计了属性权重注意力机制,增强了模型对用户细粒度偏好的捕获。最后提出了包含多行为权重生成模块和偏好迁移网络的元知识预测层,通过生成定制的元知识捕获了用户的跨行为依赖。在两个数据集上进行的大量实验验证了所提模型的有效性和优越性。

关键词: 序列推荐, 多行为推荐, 图神经网络, 注意力机制, 属性信息

Abstract: Sequential recommendation predicts users' future preferences based on the sequence of interactions between users and items.However,existing methods often overlook the multi-behavior interactions(such as page view,favorite,add to cart)in real-world scenarios.Additionally,users' preferences not only depend on temporal sequences but are also influenced by attribute information.Lastly,in the scenario of multi-behavior sequence recommendation,users' multi-behavior interactions exhibit complex dependencies.Therefore,this paper proposes a multi-behavior sequence recommendation model with attribute weights and temporal meta-knowledge(MB-ATMK).Firstly,we incorporate users' multi-behavior interaction data and design a temporal-aware encoding module based on the timestamps of user interactions to capture users' dynamic preferences through temporal-aware attention.Secondly,we introduce rich attribute information on both the user and item sides and design an attribute-weighted meta-knowledge graph neural network.Using meta-knowledge,we refine users' multi-preference patterns and design an attribute-weighted attention mechanism based on graph neural networks to enhance the model's capture of users' fine-grained preferences.Finally,we propose a meta-knowledge prediction layer that includes a multi-behavior weight generation module and a preference transfer network,capturing users' cross-behavior dependencies through generated customized meta-knowledge.Extensive experiments on two datasets validate the effectiveness and superiority of the proposed model.

Key words: Sequential recommendation, Multi-behavior recommendation, Graph neural network, Attention mechanism, Attribute information

中图分类号: 

  • TP391
[1]HE X,LIAO L,ZHANG H,et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web.2017:173-182.
[2]WANG X,HE X.Neural graph collaborative filtering[C]//Proceedings of the 42nd international ACM SIGIR Conference on Research and Development in Information Retrieval.2019:165-174.
[3]SUN F,LIU J,WU J,et al.Bert4rec:Sequential recommendation with bidirectional encoder representations from transformer[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management.2019.
[4]WU S,TANG Y,ZHU Y,et al.Session-based recommendationwith graph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019,33(1):346-353.
[5]ZHOU H,TAN Q,HUANG X,et al.Temporal augmentedgraph neural networks for session-based recommendations[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021:1798-1802.
[6]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.
[7]MA C,MA L,ZHANG Y,et al.Memory augmented graph neural networks for sequential recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020,34(4):5045-5052.
[8]TAN Q,ZHANG J,YAO J,et al.Sparse-interest network for sequential recommendation[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining.2021:598-606.
[9]CHANG J,GAO C,ZHENG Y,et al.Sequential recommendation with graph neural networks[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021:378-387.
[10]ZHANG M,WU S,YU X,et al.Dynamic graph neural networks for sequential recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2022,35(5):4741-4753.
[11]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 2020:3056-3062.
[12]YANG Y,HUANG C,XIA L,et al.Multi-behavior hypergraph-enhanced transformer for sequential recommendation[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2022:2263-2274.
[13]ZHOU H,TAN Q,HUANG X,et al.Temporal augmentedgraph neural networks for session-based recommendations[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021:1798-1802.
[14]JIANG N,ZENG Z,WEN J,et al.Incorporating multi-interestinto recommendation with graph convolution networks[J].International Journal of Intelligent Systems,2022,37(11):9192-9212.
[15]ZHAO Z,CHENG Z,HONG L,et al.Improving user topic interest profiles by behavior factorization[C]//Proceedings of the 24th International Conference on World Wide Web.2015:1406-1416.
[16]CHEN C,ZHANG M,ZHANG Y,et al.Efficient heterogeneous collaborative filtering without negative sampling for recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:19-26.
[17]CHEN C,MA W,ZHANG M,et al.Graph heterogeneous multi-relational recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:3958-3966.
[18]JAMAL M A,QI G J.Task agnostic meta-learning for few-shot learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:11719-11727.
[19]JIN B,CHENG K,QU Y,et al.Fast sparse connectivity net-work adaption via meta-learning[C]//2020 IEEE International Conference on Data Mining(ICDM).IEEE,2020:232-241.
[20]SANTORO A,BARTUNOV S,BOTVINICKM,et al.Meta-learning with memory-augmented neural networks[C]//International Confe-rence on Machine Learning.PMLR,2016:1842-1850.
[21]FINN C,ABBEEL P,LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//International Confe-rence on Machine Learning.PMLR,2017:1126-1135.
[22]CHEN M,ZHANG W,ZHANG W,et al.Meta relational lear-ning for few-shot link prediction in knowledge graphs[J].arXiv:1909.01515,2019.
[23]NIU G,LI Y,TANG C,et al.Relational learning with gated and attentive neighbor aggregator for few-shot knowledge graph completion[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021:213-222.
[24]LU Y,JIANG X,FANG Y,et al.Learning to pre-train graph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4276-4284.
[25]WEN Z,FANG Y,LIU Z.Meta-inductive node classificationacross graphs[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021:1219-1228.
[26]ACHILLE A,LAM M,TEWARI R,et al.Task2vec:Task Embedding for meta-learning[C]//Proceedings of the IEEE/CVF International conference on Computer Vision. 2019:6430-6439.
[27]XIONG W,YU M,CHANG S,et al.One-shot relational lear-ning for knowledge graphs[J].arXiv:1808.09040,2018.
[28]XIA L,HUANG C,XU Y,et al.Knowledge-enhanced hierarchical graph transformer network for multi-behavior recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4486-4493.
[29]HE X,DENG K,WANG X,et al.Lightgcn:Simplifying andpowering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:639-648.
[30]LIU F,CHENG Z,ZHU L,et al.Interest-aware message-pas-sing gcn for recommendation[C]//Proceedings of the Web Conference 2021.2021:1296-1305.
[31]WANG X,HE X,WANG M,et al.Neural graph collaborativefiltering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:165-174.
[32]JIN B,GAO C,HE X,et al.Multi-behavior recommendationwith graph convolutional networks[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:659-668.
[33]YANG Y,HUANG C,XIAL,et al.Multi-behavior hypergraph-enhanced transformer for sequential recommendation[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2022:2263-2274.
[34]KANG W C,MCAULEY J.Self-attentive sequential recommen-dation[C]//2018 IEEE International Conference on Data Mining(ICDM).IEEE,2018:197-206.
[35]WANG M,REN P,MEI L,et al.A collaborative session-based recommendation approach with parallel memory modules[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:345-354.
[36]WANG X,HE X,CAO Y,et al.Kgat:Knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Disco-very & Data Mining.2019:950-958.
[37]PENG Z,LIU H,JIA Y,et al.Attention-driven graph clustering network[C]//Proceedings of the 29th ACM International Conference on Multimedia.2021:935-943.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发