.png){kind=icon}
.png){kind=icon}
Return
Multi-modality meets re-learning: mitigating negative transfer in sequential recommendation
.png){kind=icon}
OA
AI
DOI：10.1016/j.knosys.2025.114479.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Show negative transfer in pre-training-based sequential recommendation methods. • Develop ANT to address negative transfer by using multi-modality item information. • ANT remarkably outperforms eight state-of-the-art baselines in five target tasks. • ANT does not suffer from negative transfer in the five target tasks.
Keywords:
Recommender system
Sequential recommendation
Transferable recommendation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
K
IF:
7.6
Papers:
1.2W
Citations:
4.5W