论文标题
通过应用程序的三种个性化方法
Three Approaches for Personalization with Applications to Federated Learning
论文作者
论文摘要
机器学习的标准目标是为所有用户培训单个模型。但是，在许多学习方案（例如云计算和联合学习）中，每个用户都可以学习个性化模型。在这项工作中，我们提出了对个性化的系统学习理论研究。我们建议和分析三种方法：用户聚类，数据插值和模型插值。对于所有三种方法，我们提供了学习理论保证和有效算法，我们还为此提供了经验证明的表现。我们所有的算法都是模型不足的，并且适用于任何假设类别。
The standard objective in machine learning is to train a single model for all users. However, in many learning scenarios, such as cloud computing and federated learning, it is possible to learn a personalized model per user. In this work, we present a systematic learning-theoretic study of personalization. We propose and analyze three approaches: user clustering, data interpolation, and model interpolation. For all three approaches, we provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance empirically. All of our algorithms are model-agnostic and work for any hypothesis class.
