Session-based Recommendation with Graph Neural Networks

1 Nov 2018  ·  Shu Wu, Yuyuan Tang, Yanqiao Zhu, Liang Wang, Xing Xie, Tieniu Tan ·

The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. Though achieved promising results, they are insufficient to obtain accurate user vectors in sessions and neglect complex transitions of items. To obtain accurate item embedding and take complex transitions of items into account, we propose a novel method, i.e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity. In the proposed method, session sequences are modeled as graph-structured data. Based on the session graph, GNN can capture complex transitions of items, which are difficult to be revealed by previous conventional sequential methods. Each session is then represented as the composition of the global preference and the current interest of that session using an attention network. Extensive experiments conducted on two real datasets show that SR-GNN evidently outperforms the state-of-the-art session-based recommendation methods consistently.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Session-Based Recommendations Diginetica SR-GNN MRR@20 17.59 # 9
Hit@20 50.73 # 9
Session-Based Recommendations Gowalla SR-GNN HR@20 50.32 # 1
MRR@20 24.25 # 1
Session-Based Recommendations Last.FM SR-GNN HR@20 22.33 # 3
MRR@20 8.23 # 3
Session-Based Recommendations yoochoose1 SR-GNN MRR@20 30.94 # 4
Precision@20 70.57 # 4
Session-Based Recommendations yoochoose1/4 SR-GNN MRR@20 31.89 # 4
HR@20 71.36 # 3
Session-Based Recommendations yoochoose1/64 SR-GNN MRR@20 30.94 # 9
HR@20 70.57 # 8


No methods listed for this paper. Add relevant methods here