Kernel-based Federated Learning with Personalization

by   Sudeep Salgia, et al.

We consider federated learning with personalization, where in addition to a global objective, each client is also interested in maximizing a personalized local objective. We consider this problem under a general continuous action space setting where the objective functions belong to a reproducing kernel Hilbert space. We propose algorithms based on surrogate Gaussian process (GP) models that achieve the optimal regret order (up to polylogarithmic factors). Furthermore, we show that the sparse approximations of the GP models significantly reduce the communication cost across clients.


page 1

page 2

page 3

page 4


Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process

In typical scenarios where the Federated Learning (FL) framework applies...

Personalized Federated Learning with Gaussian Processes

Federated learning aims to learn a global model that performs well on cl...

Adaptive Personalized Federated Learning

Investigation of the degree of personalization in federated learning alg...

Provably Personalized and Robust Federated Learning

Clustering clients with similar objectives and learning a model per clus...

Bandit optimisation of functions in the Matérn kernel RKHS

We consider the problem of optimising functions in the Reproducing kerne...

FedSoft: Soft Clustered Federated Learning with Proximal Local Updating

Traditionally, clustered federated learning groups clients with the same...

Communication Efficient Federated Learning for Generalized Linear Bandits

Contextual bandit algorithms have been recently studied under the federa...

Please sign up or login with your details

Forgot password? Click here to reset