Research Progress

A Novel Session-based Recommendation with Graph Neural Networks by the Center for Research on Intelligent Perception and Computing, CASIA
Aug 19, 2019Author:
PrintText Size A A

Scholars from the Center for Research on Intelligent Perception and Computing, CASIA proposes and publicizes a session-based recommendation system with graph neural networks, SR-GNN in brevity.

Session is a mechanism used to recognize and record user profile. A session-based recommendation system can help users to select certain items based on their constant behaviors in Web applications within a period of time. For instance, when someone consecutively clicks 10 goods at Taobao.com, then the 10 goods can constitute a short session. Due to the emergence of massive and anonymous information on the Internet, session-based recommendation is of great importance and widely discussed.

Under such circumstances, Shu Wu and Yanqiao Zhu, scholars from the Center for Research on Intelligent Perception and Computing, CASIA, along with other co-authors, propose a novel method, i.e. Session-Based Recommendation with Graph Neural Networks, which can outperform all the other methods at present. Related research has been published on the world top academic conference of Artificial Intelligence - AAAI 2019.

Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. 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, session sequences are modeled as graph structured data in the proposed method---SR-GNN for short. 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.

This model is available at PaddlePaddle now.

The Workflow of the SR-GNN Method

Full Text:

Shu Wu, Yuyuan Tang, Yanqiao Zhu, Liang Wang, Xing Xie, and Tieniu Tan, Session-based Recommendation with Graph Neural Networks, in AAAI 2019.  

Open Access:




ZHANG Xiaohan, Institute of Automation, Chinese Academy of Sciences

Email: xiaohan.zhang@ia.ac.cn