Attention-aware Multi-encoder for Session-based Recommendation
Jin Wu Wei, Linjie Zhang, Xiaoyan Zhu, Jianfeng Ma · 2021 IEEE Global Communications Conference (GLOBECOM) · 2021
In session-based recommendation, the user's next possible click can solely be predicted based on historical interaction behavior in the ongoing session. Previously representative works mainly use sequence models and graph neural networks to model user's behaviors of the session. These works have achieved promising results, but each also has certain defects. In view of the shortcomings of the previous works, we propose a multi-encoder framework, under which the advantages of each encoder are retained. Different encoders are used to mine different session features and finally generate a more powerful session representation to improve the recommendation result. Furthermore, in order to improve the performance of recommendation, we introduce the inter-session collaboration information by designing a Inter-session Collaboration Module. Extensive experiments on two real-world datasets demonstrate the superiority of our method over state-of-the-art algorithms.