Dynamic global structure enhanced multi-channel graph neural network for session-based recommendation

doi:10.1016/j.ins.2022.10.025

	Dynamic global structure enhanced multi-channel graph neural network for session-based recommendation
	Zhu, Xiaofei 1; Tang, Gu 1; Wang, Pengfei 2; Li, Chenliang 3; Guo, Jiafeng 4; Dietze, Stefan 5,6
	2023-05-01
发表期刊	INFORMATION SCIENCES
ISSN	0020-0255
卷号	624 页码:324-343
摘要	Session-based recommendation is a challenging task, which aims at making recommenda-tion for anonymous users based on in-session data, i.e. short-term interaction data. Most session-based recommendation methods only model user's preferences with the current session sequence, which ignore rich information from a global perspective. Meanwhile, previous works usually apply GNN to capture the transformation relationship between items, however the graph used in GNN is built through a static mode, which may introduce noise to the graph structure if user's preferences shift. In this paper, we propose a novel method called Dynamic Global Structure Enhanced Multi-channel Graph Neural Network (DGS-MGNN) to learn accurate representations of items from multiple perspectives. In DGS-MGNN, we propose a novel GNN model named Multi-channel Graph Neural Network to generate the local, global and consensus graphs dynamically and learn more informative representations of items based on the corresponding graph. Meanwhile, in order to reduce the noise information within sessions, we utilize the graph structure to assist the attention mechanism to filter noisy information within each session, so as to gen-erate an accurate intention representation for the user. Finally, combined with a repeat and explore module, a more accurate prediction probability distribution is generated. We con-duct extensive experiments on three widely used datasets, and the results demonstrate that DGS-MGNN is consistently superior to the state-of-the-art baseline models. (c) 2022 Published by Elsevier Inc.
关键词	Recommendation system Session-based recommendation Graph neural network Behavior modeling Attention model Representation learning
DOI	10.1016/j.ins.2022.10.025
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62141201] ; Major Project of Science and Technology Research Program of Chongqing Education Commission of China[KJZD-M202201102] ; Federal Ministry of Education and Research[01IS21086]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000915813400001
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/20001
专题	中国科学院计算技术研究所期刊论文
通讯作者	Zhu, Xiaofei
作者单位	1.Chongqing Univ Technol, Coll Comp Sci & Engn, Chongqing 400054, Peoples R China 2.Beijing Univ Posts & Telecommun, Sch Comp Sci, Beijing 100876, Peoples R China 3.Wuhan Univ, Sch Cyber Sci & Engn, Wuhan 430072, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 5.Leibniz Inst Social Sci, Knowledge Technol Social Sci, D-50667 Cologne, Germany 6.Heinrich Heine Univ Dusseldorf, Inst Comp Sci, D-40225 Dusseldorf, Germany
推荐引用方式 GB/T 7714	Zhu, Xiaofei,Tang, Gu,Wang, Pengfei,et al. Dynamic global structure enhanced multi-channel graph neural network for session-based recommendation[J]. INFORMATION SCIENCES,2023,624:324-343.
APA	Zhu, Xiaofei,Tang, Gu,Wang, Pengfei,Li, Chenliang,Guo, Jiafeng,&Dietze, Stefan.(2023).Dynamic global structure enhanced multi-channel graph neural network for session-based recommendation.INFORMATION SCIENCES,624,324-343.
MLA	Zhu, Xiaofei,et al."Dynamic global structure enhanced multi-channel graph neural network for session-based recommendation".INFORMATION SCIENCES 624(2023):324-343.