Three Approaches for Personalization with Applications to Federated Learning

Code

• github.com/sheetalreddy/Three-Approaches-for-Personalization-with-Applications-to-FederatedLearning
  tf★ 9

Abstract

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.

Tasks

Reproductions