arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.07855cs.IRcs.AIcs.LG
收藏

探究基于会话的推荐中的流行度偏差

Exploring Popularity Bias in Session-based Recommendation

Alipay AntGroup(支付宝蚂蚁集团)

Haowen Wang

AI总结:

本研究将推荐系统流行度偏差的倾向分析拓展至基于会话的推荐场景,调整倾向计算方法,经多领域多模型实验发现倾向特性具有数据集特异性,利用分层效应可提升模型效果。

摘要:

现有研究表明,针对用户-物品交互的推荐系统大规模离线评估易受所部署系统自身闭环反馈形式造成的偏差影响。许多研究采用倾向(propensity)概念来分析或缓解这一实证问题。在本研究中,我们将该分析拓展至基于会话的场景,并针对基于会话的推荐任务的独特特性调整了倾向计算方法。我们的实验纳入了神经模型和基于KNN的模型,覆盖音乐和电商两个领域。我们研究了不同数据集上的倾向分布和不同分层技术,发现倾向相关特性实际上是数据集特有的。随后我们利用分层效应,相较于原始模型取得了可观的结果。

英文摘要:

Existing work has revealed that large-scale offline evaluation of recommender systems for user-item interactions is prone to bias caused by the deployed system itself, as a form of closed loop feedback. Many adopt the \textit{propensity} concept to analyze or mitigate this empirical issue. In this work, we extend the analysis to session-based setup and adapted propensity calculation to the unique characteristics of session-based recommendation tasks. Our experiments incorporate neural models and KNN-based models, and cover both the music and the e-commerce domain. We study the distributions of propensity and different stratification techniques on different datasets and find that propensity-related traits are actually dataset-specific. We then leverage the effect of stratification and achieve promising results compared to the original models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑