广西师范大学学报（自然科学版） ›› 2022, Vol. 40 ›› Issue (3): 151-160.doi: 10.16088/j.issn.1001-6600.2021071405

• 研究论文 • 上一篇    下一篇

面向强化当前兴趣的图神经网络推荐算法研究

孔亚钰1+, 卢玉洁1+, 孙中天2, 肖敬先1, 侯昊辰1, 陈廷伟1*   

  1. 1.辽宁大学 信息学院, 辽宁 沈阳 110036;
    2.杜伦大学, 英国 杜伦 DH1 3LE
  • 收稿日期:2021-07-14 修回日期:2021-09-09 出版日期:2022-05-25 发布日期:2022-05-27
  • 通讯作者: 陈廷伟(1974—),男,内蒙古赤峰人,辽宁大学教授, 博士。E-mail: twchen@lnu.edu.cn
  • 作者简介:+ 共同第一作者,对本文做出了同等贡献
  • 基金资助:
    国家自然科学基金(61802160)

Research on Graph Neural Network Recommendation Algorithms for Reinforcing Current Interest

KONG Yayu1+, LU Yujie1+, SUN Zhongtian2, XIAO Jingxian1, HOU Haochen1, CHEN Tingwei1*   

  1. 1. College of Information, Liaoning University, Shenyang Liaoning 110036, China;
    2. Durham University, Durham, DH1 3LE, UK
  • Received:2021-07-14 Revised:2021-09-09 Online:2022-05-25 Published:2022-05-27

PDF (PC)

225

摘要： 在基于会话的推荐中,与传统序列建模相比,将会话序列建模为图结构在该领域表现得更为出色。但是,现有的研究方法仅利用图结构来挖掘项目之间转换特性,以此捕获用户当前兴趣的能力有限。本文提出一种面向强化当前兴趣的图神经网络推荐算法,通过引入位置嵌入,并与图神经网络相结合,从而互补顺序感知模型和图形感知模型的优势。会话序列被建模为图结构,并取原始序列的最后一次点击,通过多头注意力机制计算其对图节点信息的注意力权重,以更加准确地获取用户当前兴趣的表示。同时,在2个真实的数据集上进行验证实验,结果表明本文提出的方法实现了所有方法的最佳性能,特别是在Diginetica数据集上,所有评价指标都提升了7%以上,MRR@10指标甚至提升了9.52%,证明本文所提方法对基于会话推荐的正确性和有效性。

关键词: 基于会话的推荐, 会话图, 图神经网络, 多头注意力机制, 位置嵌入

Abstract: Compared with traditional sequence modeling in session-based recommendation, modeling the session sequence as a graph structure performs better in this field. However, the existing research methods are limited in their ability to capture user’s current interest by only using the graph structure to mine the session characteristics between items. A current interest reinforced Graph neural network for session-based recommendation is proposed in the paper. By introducing position embedding and combining with graph neural network, the advantages of sequential perception model and graph perception model are complemented. The session sequence is modeled as a graph structure. Take the last click of the original sequence, and calculate its attention weight for graph node information through the multi-head attention mechanism, so as to obtain user’s current interest expression more accurately. Extensive experiments on two real-world datasets show that, the proposed method achieved the best performance of all methods, especially on the Diginetica data set, all evaluation indicators have increased by more than 7%, and the MRR@10 indicator has even increased by 9.52%. These results show the correctness and effectiveness of the proposed method for session-based recommendation.

Key words: session-based recommendation, session graph, graph neural network, multi-head attention, position embedding

中图分类号: 

  • TP391.3
[1]SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms[C]// Proceedings of the 10th International Conference on World Wide Web. New York: ACM, 2001: 285-295.
[2]SHANI G, HECKERMAN D, BRAFMAN R I. An MDP-based recommender system[J]. Journal of Machine Learning Research, 2005, 6:1265-1295.
[3]TAN Y K, XU X X, LIU Y. Improved recurrent neural networks for session-based recommendations[C]// Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. New York: ACM, 2016: 17-22.
[4]祁明明,马文明,单荣杰.基于循环神经网络的旅游地点推荐系统设计与实现[J].电子技术与软件工程,2020(1):184-185.
[5]纪强. 基于循环神经网络的深度推荐模型研究[D].合肥:安徽大学,2020.
[6]LIU Q, ZENG Y F, MOKHOSIR, 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 & Data Mining. New York: ACM, 2018: 1831-1839.
[7]SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.
[8]WU S, TANG Y Y, ZHU Y Q, et al. Session-based recommendation with graph neural networks[C]// Proceedings of the AAAI Conference on Artificial Intelligence. California: AAAI, 2019: 346-353.
[9]LI Y J, ZEMEL R, BROCKSCHMIDT M, et al. Gated graph sequence neural networks[EB/OL].(2016-05-03)[2021-09-09].https://www.microsoft.com/en-us/research/wp-content/uploads/2015/11/1511.05493.pdf.
[10]XU C F, ZHAO P P, LIU Y C, et al. Graph contextualized self-attention network for session-based recommendation[C]// Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. California: IJCAI, 2019: 3940-3946.
[11]RENDLE S, FREUDENTHALER C, GANTNER Z. BPR: Bayesian personalized ranking from implicit feedback[C]// Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. New York: ACM, 2009:452-461.
[12]RENDLE S, FREUDENTHALER C, SCHMIDT-THIEME L. Factorizing personalized markov chains for next-basket recommendation[C]// Proceedings of the 19th International Conference on World wide web. New York: ACM, 2010: 811-820.
[13]HIDASI B, KARATZOGLOU A, BALTRUNAS L, et al. Session-based recommendations with recurrent neural networks[EB/OL].(2016-03-29)[2021-09-09]. https://arxiv.org/abs/1511.06939.
[14]ZHANG Y Y, DAI H J, XU C,et al. Sequential click prediction for sponsored search with recurrent neural networks[C]// Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence. New York: ACM, 2014:1369-1375.
[15]LI J, REN P J, CHEN Z M, et al. Neural attentive session-based recommendation[C]// Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. New York: ACM, 2017: 1419-1428.
[16]WANG P F, GUO J F, LAN Y Y, et al. Learning hierarchical representation model for next basket recommendation[C]// Proceedings of the 38th International ACM SIGIR conference on Research and Development in Information Retrieval. New York: ACM, 2015: 403-412.
[17]YANARDAG P, VISHWANATHAN S V N. Deep graph kernels[C]// Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2015: 1365-1374.
[18]MICHELI A. Neural network for graphs: a contextual constructive approach[J]. IEEE Transactions on Neural Networks, 2009, 20(3): 498-511.
[19]YU F, ZHU Y Q, LIUQ, 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. New York: ACM,2020:1921-1924.
[20]CHEN T W, 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. New York: ACM, 2020: 1172-1180.
[21]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.
[22]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.
[23]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.
[24]KANG W C, MCAULEY J L. Self-attentive sequential recommendation[C]// 2018 IEEE International Conference on Data Mining(ICDM). Piscataway,NJ:IEEE, 2018: 197-206.
[25]JI W D, WANG K Q, WANG X L, et al. Hybrid sequential recommender via time-aware attentive memory network[EB/OL].(2020-05-18)[2021-09-09]. https://arxiv.org/pdf/2005.08598v1.
[1] 吴军, 欧阳艾嘉, 张琳. 基于多头注意力机制的磷酸化位点预测模型[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 161-171.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 艾艳, 贾楠, 王媛, 郭静, 潘东东. 多性状多位点遗传关联分析的统计方法研究及其应用进展[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 1 -14 .
[2] 白德发, 徐欣, 王国长. 函数型数据广义线性模型和分类问题综述[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 15 -29 .
[3] 曾庆樊, 秦永松, 黎玉芳. 一类空间面板数据模型的经验似然推断[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 30 -42 .
[4] 张治飞, 段谦, 刘乃嘉, 黄磊. 基于Jackknife互信息的高维非线性回归模型研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 43 -56 .
[5] 杨迪, 方扬鑫, 周彦. 基于MEB和SVM方法的新类别分类研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 57 -67 .
[6] 陈钟秀, 张兴发, 熊强, 宋泽芳. 非对称DAR模型的估计与检验[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 68 -81 .
[7] 杜锦丰, 王海荣, 梁焕, 王栋. 基于表示学习的跨模态检索方法研究进展[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 1 -12 .
[8] 李慕航, 韩萌, 陈志强, 武红鑫, 张喜龙. 面向复杂高效用模式的挖掘算法综述[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 13 -30 .
[9] 晁睿, 张坤丽, 王佳佳, 胡斌, 张维聪, 韩英杰, 昝红英. 中文多模态知识库构建[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 31 -39 .
[10] 李正光, 陈恒, 林鸿飞. 基于双向语言模型的社交媒体药物不良反应识别[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 40 -48 .
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发