DeepAI
Log In Sign Up

Bandit-based Communication-Efficient Client Selection Strategies for Federated Learning

12/14/2020
by   Yae Jee Cho, et al.
0

Due to communication constraints and intermittent client availability in federated learning, only a subset of clients can participate in each training round. While most prior works assume uniform and unbiased client selection, recent work on biased client selection has shown that selecting clients with higher local losses can improve error convergence speed. However, previously proposed biased selection strategies either require additional communication cost for evaluating the exact local loss or utilize stale local loss, which can even make the model diverge. In this paper, we present a bandit-based communication-efficient client selection strategy UCB-CS that achieves faster convergence with lower communication overhead. We also demonstrate how client selection can be used to improve fairness.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/03/2020

Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies

Federated learning is a distributed optimization paradigm that enables a...
05/13/2022

Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints

Federated learning systems facilitate training of global models in setti...
03/24/2021

FedGP: Correlation-Based Active Client Selection for Heterogeneous Federated Learning

Client-wise heterogeneity is one of the major issues that hinder effecti...
06/20/2021

Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning

Shapley Value is commonly adopted to measure and incentivize client part...
07/28/2022

FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning

Data-heterogeneous federated learning (FL) systems suffer from two signi...
05/08/2021

Loss Tolerant Federated Learning

Federated learning has attracted attention in recent years for collabora...
11/11/2022

One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design

The mainstream workflow of image recognition applications is first train...