arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.05017cs.LGcs.AI
收藏

在线平台中自适应学习选择-排序

Adaptively Learning to Select-Rank in Online Platforms

Stern School of Business, New York University(纽约大学斯特恩商学院);UC Berkeley(加州大学伯克利分校);Arena Technologies(Arena科技公司);Department of Statistics, Stanford University(斯坦福大学统计系);IEDA, Hong Kong University of Science and Technology (HKUST)(香港科技大学IEDA);HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute(香港科技大学深港协同创新研究院)

Jingyuan Wang, Perry Dong, Ying Jin, Ruohan Zhan, Zhengyuan Zhou

AI总结:

本文针对在线平台异构用户的自适应排序问题,提出一种基于上下文赌博机和置信上界的排序选择算法,通过最大权重非完美匹配高效求解,实现了O(d√NKT)的累积遗憾界,并在实验上优于基线方法。

摘要:

排序算法是从电子商务网站到内容流媒体服务等各种在线平台的基础。我们的研究解决了为异构用户从候选池中自适应排序项目的挑战,这是个性化用户体验的关键组成部分。我们开发了一个用户响应模型,该模型考虑了多样化的用户偏好以及项目位置的不同影响,旨在优化用户对排序列表的整体满意度。我们将该问题构建在上下文赌博机框架内,将每个排序列表视为一个动作。我们的方法结合了置信上界来调整预测的用户满意度分数,并选择使这些调整后分数最大化的排序动作,通过最大权重非完美匹配高效求解。我们证明,在用户响应遵循广义线性模型的假设下,我们的算法在 $d$ 维上下文空间中从 $N$ 个项目中选择 $K$ 个进行排序,经过 $T$ 轮后,实现了 $O(d\sqrt{NKT})$ 的累积遗憾界。该遗憾界减轻了对环境动作空间的依赖,而环境动作空间的基数随 $N$ 和 $K$ 呈指数增长(因此使得直接应用现有自适应学习算法——如 UCB 或 Thompson 采样——不可行)。在模拟数据集和真实世界数据集上进行的实验表明,我们的算法优于基线方法。

英文摘要:

Ranking algorithms are fundamental to various online platforms across e-commerce sites to content streaming services. Our research addresses the challenge of adaptively ranking items from a candidate pool for heterogeneous users, a key component in personalizing user experience. We develop a user response model that considers diverse user preferences and the varying effects of item positions, aiming to optimize overall user satisfaction with the ranked list. We frame this problem within a contextual bandits framework, with each ranked list as an action. Our approach incorporates an upper confidence bound to adjust predicted user satisfaction scores and selects the ranking action that maximizes these adjusted scores, efficiently solved via maximum weight imperfect matching. We demonstrate that our algorithm achieves a cumulative regret bound of $O(d\sqrt{NKT})$ for ranking $K$ out of $N$ items in a $d$-dimensional context space over $T$ rounds, under the assumption that user responses follow a generalized linear model. This regret alleviates dependence on the ambient action space, whose cardinality grows exponentially with $N$ and $K$ (thus rendering direct application of existing adaptive learning algorithms -- such as UCB or Thompson sampling -- infeasible). Experiments conducted on both simulated and real-world datasets demonstrate our algorithm outperforms the baseline.

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。

↑