HybridGNN-SR: Combining Unsupervised and Supervised Graph Learning for Session-based Recommendation

被引:1
作者
Deng, Kai [1 ]
Huang, Jiajin [2 ]
Qin, Jin [1 ]
机构
[1] Guizhou Univ, Guiyang, Peoples R China
[2] Beijing Univ Technol, Beijing, Peoples R China
来源
20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW 2020) | 2020年
基金
中国国家自然科学基金;
关键词
Session-based Recommendation; Capsule Network; Variable Graph Auto-Encoder;
D O I
10.1109/ICDMW51313.2020.00028
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Session-based recommendation aims to predict the next item that a user may visit in the current session. By constructing a session graph, Graph Neural Networks (GNNs) are employed to capture the connectivity among items in the session graph for recommendation. The existing session-based recommendation methods with GNNs usually formulate the recommendation problem as the classification problem, and then use a specific uniform loss to learn session graph representations. Such supervised learning methods only consider the classification loss, which is insufficient to capture the node features from graph structured data. As unsupervised graph learning methods emphasize the graph structure, this paper proposes the HybridGNN-SR model to combine the unsupervised and supervised graph learning to represent the item transition pattern in a session from the view of graph. Specifically, in the part of unsupervised learning, we propose to combine Variational Graph Auto-Encoder (VGAE) with Mutual Information to represent nodes in a session graph; in the part of supervised learning, we employ a routing algorithm to extract higher conceptual features of a session for recommendation, which takes dependencies among items in the session into consideration. Through extensive experiments on three public datasets, we demonstrate that HybridGNN-SR outperforms a number of state-of-the-art methods on session-based recommendation by integrating the strengths of the unsupervised and supervised graph learning methods.
引用
收藏
页码:136 / 143
页数:8
相关论文
共 33 条
[1]  
[Anonymous], 2016, PROC NEURIPS
[2]  
Cho K, 2014, PREPRINT
[3]  
Gori M, 2005, IEEE IJCNN, P729
[4]  
Hidasi Balazs, 2016, ICLR
[5]  
Kipf T., 2017, ARXIV
[6]  
Klicpera J., 2019, P 7 INT C LEARNING R, P1
[7]   Multi-Interest Network with Dynamic Routing for Recommendation at Tmall [J].
Li, Chao ;
Liu, Zhiyuan ;
Wu, Mengmeng ;
Xu, Yuchi ;
Zhao, Huan ;
Huang, Pipei ;
Kang, Guoliang ;
Chen, Qiwei ;
Li, Wei ;
Lee, Dik Lun .
PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19), 2019, :2615-2623
[8]   A Capsule Network for Recommendation and Explaining What You Like and Dislike [J].
Li, Chenliang ;
Quan, Cong ;
Peng, Li ;
Qi, Yunwei ;
Deng, Yuming ;
Wu, Libing .
PROCEEDINGS OF THE 42ND INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '19), 2019, :275-284
[9]   Neural Attentive Session-based Recommendation [J].
Li, Jing ;
Ren, Pengjie ;
Chen, Zhumin ;
Ren, Zhaochun ;
Lian, Tao ;
Ma, Jun .
CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, :1419-1428
[10]   STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation [J].
Liu, Qiao ;
Zeng, Yifu ;
Mokhosi, Refuoe ;
Zhang, Haibin .
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, :1831-1839