通过建模曝光概率，让冷门内容在推荐中更易被发现。
Finding Interest Needle in Popularity Haystack: Improving Retrieval by Modeling Item Exposure
- 在检索阶段显式建模物品曝光概率并调整排序
- 线上实验显示冷门内容检索量提升25%，热门内容主导度下降40%
- 适合需要平衡公平性与用户参与度的推荐系统
推荐系统存在闭环反馈机制，导致热门内容持续被过度推荐，而小众或新内容难以获得曝光。现有偏见缓解方法如逆倾向评分（IPS）和离策略校正（OPC）主要在排序或训练阶段操作，缺乏对曝光动态的实时控制。本文提出一种暴露感知的检索打分方法，在推理时显式建模物品曝光概率，并调整检索阶段的排序。该方法将曝光影响与点击可能性解耦，可在大规模推荐平台中灵活权衡公平性与用户参与度。在线上真实视频推荐系统中进行A/B测试，结果表明：独特内容检索量提升25%，过热内容主导度降低40%，同时保持整体用户参与度稳定。本方法为检索阶段的偏见缓解提供了可扩展、可部署的新范式。
原文摘要 · Abstract (English)
Recommender systems operate in closed feedback loops, where user interactions reinforce popularity bias, leading to over-recommendation of already popular items while under-exposing niche or novel content. Existing bias mitigation methods, such as Inverse Propensity Scoring (IPS) and Off-Policy Correction (OPC), primarily operate at the ranking stage or during training, lacking explicit real-time control over exposure dynamics. In this work, we introduce an exposure-aware retrieval scoring approach, which explicitly models item exposure probability and adjusts retrieval-stage ranking at inference time. Unlike prior work, this method decouples exposure effects from engagement likelihood, enabling controlled trade-offs between fairness and engagement in large-scale recommendation platforms. We validate our approach through online A/B experiments in a real-world video recommendation system, demonstrating a 25% increase in uniquely retrieved items and a 40% reduction in the dominance of over-popular content, all while maintaining overall user engagement levels. Our results establish a scalable, deployable solution for mitigating popularity bias at the retrieval stage, offering a new paradigm for bias-aware personalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。