不上传用户数据也能实现个性化推荐，保护隐私同时保持效果。
Building a privacy-preserving Federated Recommender system for mobile devices
- 将用户偏好与敏感上下文分离处理，仅上传模型更新
- 在移动设备上用敏感信号重排序，推荐准确率损失小于5%
- 开源跨平台库，支持Android和iOS部署
在移动端提供个性化内容的传统方式需将敏感用户数据集中存储，这与现代隐私期望和地理监管日益冲突。我们提出一种两阶段联邦推荐系统，通过原则性分离非敏感的用户偏好数据与始终留在设备上的敏感移动上下文数据。第一阶段在云端运行协同过滤模型，基于非敏感的应用上下文数据生成候选列表；第二阶段在设备端利用敏感移动信号对候选进行重排序，仅上传模型更新或梯度。我们在MovieLens、UCI人体活动识别数据集及一个专有试点数据集上验证该方法，并提供可投入生产的Kotlin Multiplatform库，支持Android和iOS部署。
原文摘要 · Abstract (English)
Serving personalized content on mobile devices has traditionally required pooling sensitive user data on centralized servers, a practice increasingly at odds with modern privacy expectations and geographical regulations. We present a two-stage federated recommendation system pipeline for mobile devices, built around a principled separation between non-sensitive user preference data and sensitive mobile context data that never leaves the device. The first stage runs a collaborative filtering model on non-sensitive app-context data in the cloud to generate a shortlist of relevant items. The second stage re-ranks these candidates on-device using sensitive mobile signals, with only model updates/gradients ever leaving the device. We validate the approach on MovieLens, UCI Human Activity Recognition, and a proprietary pilot dataset, and deliver a production-ready implementation as a Kotlin Multiplatform library deployable on Android and iOS.
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。