University of Oulu

Communication-efficient scheduling policy for federated learning under channel uncertainty

Saved in:
Author: Manimel Wadu, Madhusanka1
Organizations: 1University of Oulu, Faculty of Information Technology and Electrical Engineering, Communications Engineering
Format: ebook
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 1.4 MB)
Pages: 43
Persistent link: http://urn.fi/URN:NBN:fi:oulu-201912213414
Language: English
Published: Oulu : M. Manimel Wadu, 2019
Publish Date: 2020-01-07
Thesis type: Master's thesis
Tutor: Bennis, Mehdi
Reviewer: Bennis, Mehdi
Samarakoon, Sumudu
Description:

Abstract

Federated learning (FL) is a promising decentralized training method for on-device machine learning. Yet achieving a performance close to a centralized training via FL is hindered by the client-server communication. In this work, a novel joint client scheduling and resource block (RB) allocation policy is proposed to minimize the loss of accuracy in FL over a wireless system with imperfect channel state information (CSI) compared to a centralized training-based solution. First, the accuracy loss minimization problem is cast as a stochastic optimization problem over a predefined training duration. In order to learn and track the wireless channel under imperfect CSI, a Gaussian process regression (GPR)-based channel prediction method is leveraged and incorporated into the scheduling decision. Next, the client scheduling and RB allocation policy is derived by solving the aforementioned stochastic optimization problem using the Lyapunov optimization framework. Then, the aforementioned solution is extended for scenarios with perfect CSI. Finally, the proposed scheduling policies for both perfect and imperfect CSI are evaluated via numerical simulations. Results show that the proposed method reduces the accuracy loss up to 25.8% compared to FL client scheduling and RB allocation policies in the existing literature.

see all

Subjects:
Copyright information: © Madhusanka Manimel Wadu, 2019. This publication is copyrighted. You may download, display and print it for your own personal use. Commercial use is prohibited.