Three Approaches for Personalization with Applications to Federated Learning
Three Approaches for Personalization with Applications to Federated Learning
复制标题
DOI：
--
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Y. Mansour;M. Mohri;Jae Ro;A. Suresh
中科院分区：
文献类型：
--
作者：
Y. Mansour;M. Mohri;Jae Ro;A. Suresh
机器学习的标准目标是为所有用户训练一个模型。然而，在许多学习场景中，例如云计算和联合学习，可以为每个用户学习个性化模型。在这项工作中，我们提出了一个系统的学习理论研究的个性化。我们提出并分析了三种方法：用户聚类，数据插值和模型插值。对于所有这三种方法，我们提供了学习理论的保证和有效的算法，我们也证明了经验的性能。我们所有的算法都是模型不可知的，适用于任何假设类。
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.