.png){kind=icon}
返回
Long-tail session-based recommendation from calibration
.png){kind=icon}
OA
AI
DOI：10.1007/s10489-022-03718-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Accurate predictions in session-based recommendations have progressed, but a few studies have focused on skewed recommendation lists caused by popularity bias. Existing models for mitigating popularity bias have attempted to reduce the overconcentration of popular items by amplifying scores of less popular items. However, they normally ignore the users' different preferences toward long-tail items. Thus, we incorporate calibration, where calibrated recommendations reflect the users' interests in recommendation lists with appropriate proportions, to mitigate the popularity bias from the user's perspective. Specifically, we propose a calibration module to predict the ratio of tail items in the recommendation list from the session representation, and align it to the ongoing session. Additionally, we utilize a two-stage curriculum training strategy to improve prediction in the calibration module. Experiments on benchmark datasets show that our model can both achieve the competitive accuracy of recommendation and provide more tail items.
Keyword:
Session-based recommendation
Long-tail
Popularity bias
Calibration
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Ultrasonic Guided Wave Characterization and Inspection of Laminate Fiber-Reinforced Composite Plates
PREAI
分享收藏Improving graph neural network for session-based recommendation system via non-sequential interactions.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Iterative rating prediction for neighborhood-based collaborative filtering基于邻域的协同过滤迭代评分预测APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏
查看更多内容