Dynamic intent-aware iterative denoising network for session-based recommendation

作者：

Highlights：

• We solve dynamic change of user intents and uncertainty of user behaviors in SBR.

• We model the dynamic user intents by exploiting personalized item embeddings.

• We devise a novel iterative denoising module to explicitly denoise sessions.

• Extensive experimental results demonstrate the effectiveness of the proposed DIDN.

摘要

•We solve dynamic change of user intents and uncertainty of user behaviors in SBR.•We model the dynamic user intents by exploiting personalized item embeddings.•We devise a novel iterative denoising module to explicitly denoise sessions.•Extensive experimental results demonstrate the effectiveness of the proposed DIDN.

论文关键词：Session-based recommendation,Dynamic intents,Uncertain behavior,Attention mechanism

论文评审过程：Received 17 December 2021, Revised 25 February 2022, Accepted 24 March 2022, Available online 28 April 2022, Version of Record 28 April 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.102936