MGR: Metric Learning with Graph Neural Networks for Multi-behavior Recommendation

被引:0
作者
Yuan, Yuan [1 ]
Tang, Yan [1 ]
Du, Luomin [1 ]
Chen, Yingpei [1 ]
机构
[1] Southwest Univ, Coll Comp & Informat Sci, Chongqing, Peoples R China
来源
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I | 2022年 / 13368卷
关键词
Recommender system; Knowledge graph; Graph neural networks; Temporal information; Metric learning;
D O I
10.1007/978-3-031-10983-6_36
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditional recommendation methods often suffer from the problems of sparsity and cold start. Therefore, researchers usually leverage Knowledge Graph as a kind of side information to alleviate these issues and improve the accuracy of recommendation results. However, most existing studies focus on modeling the single behavior of user-item interactions, ignoring the active effects of the multi-type behavior information in the recommendation performance. In view of this, we propose Metric Learning with Graph Neural Networks for Multi-behavior Recommendation (MGR), a novel sequential recommendation framework that considers both temporal dynamics and semantic information. Specifically, the temporal encoding strategy is used to model dynamic user preferences. In addition, the Graph Neural Network is utilized to capture the information from high-order nodes so as to mine the semantic description in multi-behavior interactions. Finally, symmetric metric learning helps to sort the item list to accomplish the Top-K recommendation task. Extensive experiments in three real-world datasets demonstrate that MGR outperforms the state-of-the-art recommendation methods.
引用
收藏
页码:466 / 477
页数:12
相关论文
共 50 条
[41]   How Expressive are Graph Neural Networks in Recommendation? [J].
Cai, Xuheng ;
Xia, Lianghao ;
Ren, Xubin ;
Huang, Chao .
PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2023, 2023, :173-182
[42]   Dynamic Graph Neural Networks for Sequential Recommendation [J].
Zhang, Mengqi ;
Wu, Shu ;
Yu, Xueli ;
Liu, Qiang ;
Wang, Liang .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (05) :4741-4753
[43]   Separated Graph Neural Networks for Recommendation Systems [J].
Sun, Jianwen ;
Gao, Lu ;
Shen, Xiaoxuan ;
Liu, Sannyuya ;
Liang, Ruxia ;
Du, Shangheng ;
Liu, Shengyingjie .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (01) :382-393
[44]   Hybrid music recommendation with graph neural networks [J].
Bevec, Matej ;
Tkalcic, Marko ;
Pesek, Matevz .
USER MODELING AND USER-ADAPTED INTERACTION, 2024, 34 (05) :1891-1928
[45]   Graph-based Recommendation using Graph Neural Networks [J].
Dossena, Marco ;
Irwin, Christopher ;
Portinale, Luigi .
2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA, 2022, :1769-1774
[46]   Time-based Knowledge-aware framework for Multi-Behavior Recommendation [J].
Li, Xiujuan ;
Wang, Nan ;
Liu, Xin ;
Zeng, Jin ;
Li, Jinbao .
EXPERT SYSTEMS WITH APPLICATIONS, 2025, 273
[47]   Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling [J].
Xia, Lianghao ;
Huang, Chao ;
Xu, Yong ;
Dai, Peng ;
Lu, Mengyin ;
Bo, Liefeng .
2021 IEEE 37TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2021), 2021, :1931-1936
[48]   Contrastive Multi-Level Graph Neural Networks for Session-Based Recommendation [J].
Wang, Fuyun ;
Gao, Xingyu ;
Chen, Zhenyu ;
Lyu, Lei .
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 :9278-9289
[49]   Multi-View Graph Contrastive Neural Networks for Session-Based Recommendation [J].
Huang, Pengbo ;
Wang, Chun .
MATHEMATICS, 2025, 13 (09)
[50]   SiReN: Sign-Aware Recommendation Using Graph Neural Networks [J].
Seo, Changwon ;
Jeong, Kyeong-Joong ;
Lim, Sungsu ;
Shin, Won-Yong .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (04) :4729-4743