Three Approaches for Personalization with Applications to Federated Learning

TLDR

Standard machine learning trains a single model for all users, but in settings such as cloud computing and federated learning, personalized models per user can be learned. In this work, we present a systematic learning‑theoretic study of personalization. We propose and analyze three model‑agnostic approaches—user clustering, data interpolation, and model interpolation—that apply to any hypothesis class. For all three approaches, we provide learning‑theoretic guarantees and efficient algorithms, and we demonstrate their empirical performance.

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.