Federated Learning

Chapter 7: Personalized federated learning: theory and open problems

Canh T. Dinh^a; Tung T. Vu^b; Nguyen H. Tran^a    aThe University of Sydney, Darlington, NSW, Australia^bQueen's University Belfast, Belfast, United Kingdom

Abstract

Federated Learning (FL) is a distributed and privacy-preserving machine learning technique in which a group of clients collaborates with a server to learn a global model without sharing clients' data. One challenge with FL is statistical diversity among clients, which restricts the global model from delivering good performance on each client's task. A common approach to address this challenge is to find a “personalized model” that is stylized for each client's data. This chapter introduces and reviews several current personalized ...