广东工业大学学报

• • 上一篇    下一篇

基于因子级特征与属性偏好联合学习的会话推荐

林浩, 陈平华   

  1. 广东工业大学 计算机学院, 广东 广州 510006
  • 收稿日期:2023-12-28 出版日期:2024-05-25 发布日期:2024-05-25
  • 通信作者: 陈平华(1967-),男,教授,主要研究方向为人工智能、大数据,E-mail:phchen@gdut.edu.cn
  • 作者简介:林浩(1998-),男,硕士研究生,主要研究方向为图神经网络、推荐系统,E-mail:1695942074@qq.com
  • 基金资助:
    广东省重点领域研发计划项目(2021B0101200002)；广东省自然科学基金资助项目(2021A1515012233)

Factor-level Feature and Attribute Preference Joint Learning Based Session Recommendation

Lin Hao, Chen Ping-hua   

  1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2023-12-28 Online:2024-05-25 Published:2024-05-25

HTML

PDF (PC)

9

摘要： 针对序列短、数据稀疏、难以泛化导致的会话推荐准确率不高问题，提出了因子级特征与属性偏好联合学习的会话推荐模型。模型首先通过构建全局级会话项目依赖感知图，学习用户全局级会话项目嵌入；然后，应用解纠缠表示学习方法将会话中的项目分解为多个相对独立的因子级特征，学习用户因子级兴趣偏好；接着利用情境化自注意图神经网络捕获用户针对会话项目属性的偏好；最后，将因子级兴趣偏好与项目属性偏好联合学习，得到用户最终兴趣偏好表示，并最终完成会话推荐。在Diginetica、Cosmetics两个公开数据集上的多个实验表明，本文模型优于对比的基线模型，验证了本文模型的良好推荐性能和设计合理性。

关键词: 会话推荐, 因子级特征, 解纠缠表示, 全局项目依赖, 图神经网络

Abstract: A factor-level feature and attribute preference joint learning session-based recommendation model is proposed to address the problem of low recommendation accuracy caused by short sequences, sparse data, and difficulty in generalization. The model first learns user global-level session item embeddings by constructing a global level session item dependency perception graph. Then, using the method of disentanglement representation learning, the items in the conversation are decomposed into multiple relatively independent factor-level features to learn user factor-level interest preferences. Then, using contextualized self-attention graph neural networks, user preferences for session item attributes are captured. Finally, factor-level interest preferences and the project attribute preferences are jointly learned to obtain the user's final interest preferences, which in turn completes the session recommendation. Multiple experiments on two publicly available datasets, Diginetica and Cosmetics, have shown that our model outperforms the baseline model in comparison, verifying the recommendation performance and design rationality of our model.

Key words: session-based recommendation, factor-level feature, disentangled representation learning, global-level item dependency, graph neural network

中图分类号: 

  • TP391
[1] HE Z, LIU W, GUO W, et al. A survey on user behavior modeling in recommender systems[C]//International Joint Conference on Artificial Intelligence. Macao: IJCAI, 2023: 6656-6664.
[2] YAP G E, LI X L, YU P S. Effective next-items recommendation via personalized sequential pattern mining[C]//Database Systems for Advanced Applications. Busan: Springer Berlin Heidelberg, 2012: 48-64.
[3] LUDEWIG M, JANNACH D. Evaluation of session-based recommendation algorithms [J]. User Modeling and User-Adapted Interaction, 2018, 28(4): 331-390.
[4] LI J, REN P, CHEN Z, et al. Neural attentive session-based recommendation[C]//ACM on Conference on Information and Knowledge Management. New York: Association for Computing Machinery, 2017: 1419-1428.
[5] GAO C, ZHENG Y, LI N, et al. A survey of graph neural networks for recommender systems: challenges, methods and directions [J]. ACM Transactions on Recommender Systems, 2021, 1(3): 1-51.
[6] 林穗, 郑志豪. 基于关联规则的客户行为建模与商品推荐研究[J]. 广东工业大学学报, 2018, 35(3): 90-94.
LIN S, ZHENG Z H. A research of a recommender system-based on customer behavior modeling by mining association rules [J]. Journal of Guangdong University of Technology, 2018, 35(3): 90-94.
[7] RENDLE S, FREUDENTHALER C, SCHMIDT-THIEMEL. Factorizing personalized markov chains for next-basket recommendation[C]//World Wide Web Conference. New York: Association for Computing Machinery, 2010: 811-820
[8] WU X, LIU Q, CHEN E, et al. Personalized next-song recommendation in online karaokes[C]//ACM Conference on Recommender Systems. New York: Association for Computing Machinery, 2013: 137-140.
[9] HIDASI B, KARATZOGLOU A, BALTRUNAS L, et al. Session-based recommendations with recurrent neural networks[C]//International Conference on Learning Representations. San Juan: ICLR, 2016: 1-10.
[10] CEN Y, ZHANG J, ZOU X, et al. Controllable multi-interest framework for recommendation[C]//ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: Association for Computing Machinery, 2020: 2942-2951.
[11] WU S, TANG Y, ZHU Y, et al. Session-based recommendation with graph neural networks[C]//AAAI Conference on Artificial Intelligence. Honolulu: AAAI, 2019: 346-353.
[12] WANG M, REN P, MEI L, et al. A collaborative session-based recommendation approach with parallel memory modules[C]//ACM SIGIR Conference on Research and Development in Information Retrieval. New York: Association for Computing Machinery, 2019: 345-354.
[13] 杨显鹏, 李晓楠, 李冠宇. 基于超图卷积网络的用户微行为会话推荐[J]. 计算机工程与应用, 2023, 59(16): 108-114.
YANG X P, LI X N, LI G Y. Hypergraph convolutional networks for user micro-behavior session-based recommendation [J]. Computer Engineering and Applications., 2023, 59(16): 108-114.
[14] LIN Z, TIAN C, HOU Y, et al. Improving graph collaborative filtering with neighborhood-enriched contrastive learning[C]//ACM Web Conference. New York: Association for Computing Machinery, 2022: 2320-2329.
[15] XIA X, YIN H, YU J, et al. Self-supervised graph co-training for session-based recommendation[C]//ACM International Conference on Information & Knowledge Management. New York: Association for Computing Machinery, 2021: 2180-2190.
[16] WANG X, JIN H, ZHANG A, et al. Disentangled graph collaborative filtering[C]//ACM SIGIR Conference on Research and Development in Information Retrieval. New York: Association for Computing Machinery, 2020: 1001-1010.
[17] SZÉKELY G J, RIZZO M L, BAKIROV N K. Measuring and testing dependence by correlation of distances [J]. Annals of Statistics, 2007, 35(6): 2769-2794.
[18] ZHENG Y, GAO C, HE X, et al. Price-aware recommendation with graph convolutional networks[C]//IEEE 36th International Conference on Data Engineering (ICDE) . Online: IEEE, 2020: 133-144.
[19] ZHANG X, XU B, YANG L, et al. Price does matter! modeling price and interest preferences in session-based recommendation[C]//ACM SIGIR Conference on Research and Development in Information Retrieval. New York: Association for Computing Machinery, 2022: 1684-1693.
[20] GREENSTEIN-MESSICA A, ROKACH L. Personal price aware multi-seller recommender system: evidence from eBay [J]. Knowledge-Based Systems, 2018, 150: 14-26.
[21] ANH P H, BACH N X, PHUONG T M. Session-based recommendation with self-attention[C]//International Symposium on Information and Communication Technology. New York: Association for Computing Machinery, 2019: 1-8.
[22] WANG Z, WEI W, CONG G, et al. Global context enhanced graph neural networks for session-based recommendation[C]//ACM SIGIR Conference on Research and Development in Information Retrieval. New York: Association for Computing Machinery, 2020: 169-178.
[23] LU Y, ZENG J, ZHANG J, et al. Attention calibration for transformer in neural machine translation[C]//Annual Meeting of the Association for Computational Linguistics. Online: Association for Computational Linguistics, 2021: 1288-1298.
[24] XIA X, YIN H, YU J, et al. Self-supervised hypergraph convolutional networks for session-based recommendation[C]//AAAI Conference on Artificial Intelligence. Vancouver: AAAI, 2021, 35(5) : 4503-4511.
[25] FAN Z, LIU Z, WANG Y, et al. Sequential recommendation via stochastic self-attention[C]//Proceedings of the ACM Web Conference. New York: Association for Computing Machinery, 2022: 2036-2047.
[1] 郑侠聪, 程良伦, 黄国恒, 王敬超. 嵌入拓扑特征的自然场景文本检测方法[J]. 广东工业大学学报, 2024, 41(03): 102-109.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发