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 2401.04053cs.IR
收藏

基于嵌套反馈的排序学习

Learning-to-Rank with Nested Feedback

Hitesh Sagtani, Olivier Jeunen, Aleksei Ustimenko

AI总结:

针对嵌套列表场景,提出一种有理论依据的方法将二级反馈整合到一级排序模型中,并在大规模推荐系统的在线实验中证实了其理论发现。

摘要:

网络上的许多平台向用户展示内容排序列表,通常针对参与度、满意度或留存率驱动的指标进行优化。Learning-to-Rank (LTR) 研究文献的进展促进了该应用领域的快速增长。目前一些流行的界面包含了嵌套列表,用户可以通过任意一级条目进入二级信息流。这自然对评估指标、目标函数以及我们期望学习的排序策略产生了影响。我们提出了一种有理论依据的方法,将二级反馈整合到任何一级排序模型中。在大规模推荐系统上的在线实验证实了我们的理论发现。

英文摘要:

Many platforms on the web present ranked lists of content to users, typically optimized for engagement-, satisfaction- or retention- driven metrics. Advances in the Learning-to-Rank (LTR) research literature have enabled rapid growth in this application area. Several popular interfaces now include nested lists, where users can enter a 2nd-level feed via any given 1st-level item. Naturally, this has implications for evaluation metrics, objective functions, and the ranking policies we wish to learn. We propose a theoretically grounded method to incorporate 2nd-level feedback into any 1st-level ranking model. Online experiments on a large-scale recommendation system confirm our theoretical findings.

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。

↑