Graph-Based Sequential Interpolation Recommender for Cold-Start Users

被引:0
作者
Li, Aoran [1 ]
Wu, Jiajun [1 ]
Xu, Shuai [1 ,2 ]
Zang, Yalei [1 ]
Liu, Yi [1 ]
Lu, Jiayi [1 ]
Zhao, Yanchao [1 ]
Wang, Gaoxu [3 ]
Meng, Qing [4 ]
Fu, Xiaoming [5 ]
机构
[1] Nanjing Univ Aeronaut & Astronaut, Nanjing, Peoples R China
[2] Nanjing Univ, State Key Lab Novel Software Technol, Nanjing, Peoples R China
[3] Nanjing Hydraul Res Inst, Nanjing, Peoples R China
[4] Singapore Univ Technol & Design, Singapore, Singapore
[5] Univ Goettingen, Gottingen, Germany
来源
WEB AND BIG DATA, PT III, APWEB-WAIM 2022 | 2023年 / 13423卷
关键词
Recommendation systems; Cold-start; Graph neural network;
D O I
10.1007/978-3-031-25201-3_5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sequential recommendation systems aim to capture the users' dynamic preferences from users' historical interactions to provide more accurate recommendations. However, in many scenarios, there are a large number of cold-start users with limited user-item interactions. To address this challenge, some studies utilize auxiliary information to infer users' interests. But with the increasing awareness of personal privacy protection, it is difficult to obtain detailed descriptions of users. Therefore, we propose a model called GitRec (Graph-based sequential interpolation Recommender for cold-start users) to address this issue. Our proposed model GitRec captures users' latent preferences and provides more proper recommendations for cold-start users without any help from external information. Specifically, (i) GitRec constructs the global graph based on all sequences to obtain the core interests of the warmstart users. (ii) Then, GitRec selects content-rich sequences that are most similar to the short sequences and constructs the local graph to find out the potential preferences of cold-start users. (iii) Finally, GitRec can find suitable candidates to enrich the information of the cold-start users by using graph neural networks, and provide better recommendations with the help of core interests and potential preferences. We conducted extensive experiments on three real-world datasets. The experimental results demonstrate that GitRec has significant improvement over state-of-the-art methods.
引用
收藏
页码:57 / 71
页数:15
相关论文
共 29 条
[1]  
[Anonymous], 2010, P 19 INT C WORLD WID, DOI DOI 10.1145/1772690.1772773
[2]  
Chaozhuo Li, 2015, Web Information Systems Engineering - WISE 2015. 16th International Conference. Proceedings: LNCS 9419, P276, DOI 10.1007/978-3-319-26187-4_24
[3]   Co-purchaser Recommendation for Online Group Buying [J].
Chen, Jihong ;
Chen, Wei ;
Huang, Jinjing ;
Fang, Jinhua ;
Li, Zhixu ;
Liu, An ;
Zhao, Lei .
DATA SCIENCE AND ENGINEERING, 2020, 5 (03) :280-292
[4]   Towards Conversational Recommender Systems [J].
Christakopoulou, Konstantina ;
Radlinski, Filip ;
Hofmann, Katja .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :815-824
[5]   Reinforced KGs reasoning for explainable sequential recommendation [J].
Cui, Zhihong ;
Chen, Hongxu ;
Cui, Lizhen ;
Liu, Shijun ;
Liu, Xueyan ;
Xu, Guandong ;
Yin, Hongzhi .
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2022, 25 (02) :631-654
[6]   Alleviating the new user problem in collaborative filtering by exploiting personality information [J].
Fernandez-Tobias, Ignacio ;
Braunhofer, Matthias ;
Elahi, Mehdi ;
Ricci, Francesco ;
Cantador, Ivan .
USER MODELING AND USER-ADAPTED INTERACTION, 2016, 26 (2-3) :221-255
[7]  
He RN, 2016, IEEE DATA MINING, P191, DOI [10.1109/ICDM.2016.0030, 10.1109/ICDM.2016.88]
[8]   New technique to alleviate the cold start problem in recommender systems using information from social media and random decision forests [J].
Herce-Zelaya, J. ;
Porcel, C. ;
Bernabe-Moreno, J. ;
Tejeda-Lorente, A. ;
Herrera-Viedma, E. .
INFORMATION SCIENCES, 2020, 536 :156-170
[9]   Recurrent Neural Networks with Top-k Gains for Session-based Recommendations [J].
Hidasi, Balazs ;
Karatzoglou, Alexandros .
CIKM'18: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2018, :843-852
[10]   Path-enhanced explainable recommendation with knowledge graphs [J].
Huang, Yafan ;
Zhao, Feng ;
Gui, Xiangyu ;
Jin, Hai .
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2021, 24 (05) :1769-1789