.png){kind=icon}
.png){kind=icon}
Return
DiffSBR: A diffusion model for session-based recommendation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2025.104284.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• This study addresses the issue of homogeneous and heterogeneous preferences in SBR. • Combining Transformer and hypergraph convolution for local and global modeling. • Cluster-aware diffusion model effectively represents preference as distribution. • Experimental results demonstrate DiffSBR’s superior recommendation performance.
Keywords:
Session-based recommendation
Diffusion model
Graph neural network
User preference modeling
Journal
I
IF:
6.9
Papers:
5.2K
Citations:
1.4W