… Federated learning (FL) is a distributed machine learning paradigm which allows for model
training on decentralized data residing on devices without breaching data privacy. Hence, FL …

… communication efficiency are two critical ones that hinder the development of federated
learning… a personalized and communication-efficient federated learning framework via exploiting …

… propose a personalization approach for federated learning and … Following the statistical
learning theory, in a federated learning … a communication efficient adaptive algorithm to learn the …

… a novel personalized federated learning framework in a decentralized (peer-to-peer)
communication … In this work, we propose a novel personalized federated learning framework in a …

Personalized federated learning (PFL) aims to train model(s) that can perform well on the
individual edge-devices' data where the edge-devices (clients) are usually IoT devices like our …

… Personalized Federated Learning faces many challenges such as expensive communication
costs, training-… models to achieve personalization. We follow the avenue and propose a …

… Federated learning (FL) has been widely deployed in edge … for communication-efficient and
personalized federated learning, … communication overhead. Moreover, each client learns a …

… personalization in an end-to-end manner and significantly improve both communication
efficiency … We design LotteryFL – a communication-efficient and personalized FL framework. The …

Federated learning (FL) enables edge devices, such as Internet of Things devices (eg, sensors),
servers, and institutions (eg, hospitals), to collaboratively train a machine learning (ML) …

… and communication efficiency at the same time. … training models from a set C of clients
without sharing their local data. In this paper, we focus on the personalized federated learning prob…