发表机构
Georgia Institute of Technology; Amazon Music（佐治亚理工学院; 亚马逊音乐）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究从动力学系统视角探究推荐系统流行度偏差的产生机制，构建随机过程与ODE框架推导相关条件，并通过合成数据和真实音乐推荐日志验证理论结果。
AI 中文摘要
推荐系统中的流行度偏差产生于多数用户群体生成不成比例的交互数据，导致系统愈发偏向该群体，同时降低对小众用户的推荐质量。尽管已有大量流行度偏差的实证证据，但其产生的动力学机制尚未被充分理解。本研究从动力学系统视角探究推荐器模型更新与用户参与度的耦合演化，构建随机过程并基于两时间尺度随机近似的常微分方程（ODE）框架分析其渐近行为，刻画该动力学系统的平衡点，推导可严格证明流行度会涌现的条件，以及所有用户群体可实现对称留存的条件。在合成数据和源自某大型商业音乐推荐平台的真实生产日志上开展实验，以验证理论结果。
英文摘要
Popularity bias in recommendation systems arises when a majority user class generates disproportionate interaction data, causing the system to increasingly favour it while degrading recommendation quality for niche users. While extensive empirical evidence of popularity bias exists, the dynamics leading to its emergence are not well understood. In this work, we study the coupled evolution of recommender model updates and user engagement through the lens of dynamical systems. We formulate a stochastic process and analyse its asymptotic behaviour through an ordinary differential equation (ODE) framework grounded in two-time-scale stochastic approximation. We characterise the equilibrium points of this dynamical system, and derive conditions under which popularity bias is provably emergent, as well as conditions under which symmetric retention of all user classes is possible. We conduct experiments on synthetic data and real-world production logs derived from a large-scale commercial music recommendation platform to validate our theoretical results.
