用户可自主控制推荐目标，实现本地化隐私保护推荐。
Beyond Centralization: User-Controlled Federated Recommendations in Practice
- 用户在本地设备上控制推荐目标，数据不上传。
- 65.37%点击率优于中心化系统，用户主动调整设置248次。
- 适合关注隐私与个性化平衡的推荐系统研究者。
推荐系统通常依赖集中式用户数据，限制用户控制并引发隐私担忧。联邦学习通过将数据保留在设备端提供替代方案，但其对真实用户行为的影响仍不明确。我们部署了一个真实的联邦推荐系统，让用户在本地控制推荐目标，同时保持数据私密。在为期53天、22名参与者和8807个内容项的实验中，用户在个性化与多样性推荐间切换。结果显示，当用户拥有明确选择权时，个性化推荐的点击率达65.37%，高于中心化系统的62.07%；用户积极使用控制功能（满意度3.93/5，共248次设置变更），并通过即时反馈理解自身行为对推荐的影响。结果表明，用户控制、隐私保护与有效个性化可在实际系统中协同实现。本研究展示了一种可交互、隐私友好的推荐实践方案。代码与演示材料见：https://github.com/SlokomManel/federated-recommendations-participants
原文摘要 · Abstract (English)
Recommendation systems typically require centralized user data, limiting user control and raising privacy concerns. Federated learning offers an alternative by keeping data on-device, but its impact on real user behavior remains largely unexplored. We present a live federated recommender system that allows users to control the recommendation objective while keeping their data local. In a 53-day deployment with 22 participants and a catalog of 8807 titles, users interacted with recommendations and switched between personalization and diversity-enhanced ranking. We find that users prefer personalization when given explicit choice (65.37\% vs.\ 62.07\% CTR), actively engage with control mechanisms (3.93/5 satisfaction; 248 settings changes), and develop an understanding of how their interactions affect recommendations through immediate feedback. Our results show that user control, privacy, and effective personalization can be combined in a working system. We demonstrate a practical approach to interactive, privacy-preserving recommendation. Code and demo materials are available at: https://github.com/SlokomManel/federated-recommendations-participants
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。