.png){kind=icon}
Return
Frequency-sensitive diffusion model for personalized sequential recommendation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.131313.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Our methodology integrates frequency-based statistical measures with probabilistic diffusion frameworks to mimic human reasoning, capturing the complexities of cognitive processes. • To adapt the diffusion model for recommendation, we optimize both the forward and reverse processes, integrating high- and low-frequency considerations while balancing temporal realism. • Our methodology integrates global and local perspectives of augmented sequences across multiple scales and dimensions to effectively capture user intent. The use of contrastive learning techniques enhances our model’s performance.
Keywords:
diffusion model
recommendation system
contrastive learning
user intent
frequency-based statistics
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
No cited papers available