On the Convergence Time of Federated Learning Over Wireless Networks Under Imperfect CSI

04/01/2021
by   Francesco Pase, et al.
1

Federated learning (FL) has recently emerged as an attractive decentralized solution for wireless networks to collaboratively train a shared model while keeping data localized. As a general approach, existing FL methods tend to assume perfect knowledge of the Channel State Information (CSI) during the training phase, which may not be easy to acquire in case of fast fading channels. Moreover, literature analyses either consider a fixed number of clients participating in the training of the federated model, or simply assume that all clients operate at the maximum achievable rate to transmit model data. In this paper, we fill these gaps by proposing a training process that takes channel statistics as a bias to minimize the convergence time under imperfect CSI. Numerical experiments demonstrate that it is possible to reduce the training time by neglecting model updates from clients that cannot sustain a minimum predefined transmission rate. We also examine the trade-off between number of clients involved in the training process and model accuracy as a function of different fading regimes.

READ FULL TEXT

page 1

page 6

research
05/19/2022

CHARLES: Channel-Quality-Adaptive Over-the-Air Federated Learning over Wireless Networks

Over-the-air federated learning (OTA-FL) has emerged as an efficient mec...
research
06/12/2021

Joint Client Scheduling and Resource Allocation under Channel Uncertainty in Federated Learning

The performance of federated learning (FL) over wireless networks depend...
research
02/03/2020

Federated Learning under Channel Uncertainty: Joint Client Scheduling and Resource Allocation

In this work, we propose a novel joint client scheduling and resource bl...
research
01/16/2019

Coded Federated Computing in Wireless Networks with Straggling Devices and Imperfect CSI

Distributed computing platforms typically assume the availability of rel...
research
01/13/2022

Jamming Attacks on Federated Learning in Wireless Networks

Federated learning (FL) offers a decentralized learning environment so t...
research
10/19/2020

Blind Federated Edge Learning

We study federated edge learning (FEEL), where wireless edge devices, ea...
research
07/24/2023

Imperfect CSI: A Key Factor of Uncertainty to Over-the-Air Federated Learning

Over-the-air computation (AirComp) has recently been identified as a pro...

Please sign up or login with your details

Forgot password? Click here to reset