Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective

04/09/2020
by   Jie Xu, et al.
0

This paper studies federated learning (FL) in a classic wireless network, where learning clients share a common wireless link to a coordinating server to perform federated model training using their local data. In such wireless federated learning networks (WFLNs), optimizing the learning performance depends crucially on how clients are selected and how bandwidth is allocated among the selected clients in every learning round, as both radio and client energy resources are limited. While existing works have made some attempts to allocate the limited wireless resources to optimize FL, they focus on the problem in individual learning rounds, overlooking an inherent yet critical feature of federated learning. This paper brings a new long-term perspective to resource allocation in WFLNs, realizing that learning rounds are not only temporally interdependent but also have varying significance towards the final learning outcome. To this end, we first design data-driven experiments to show that different temporal client selection patterns lead to considerably different learning performance. With the obtained insights, we formulate a stochastic optimization problem for joint client selection and bandwidth allocation under long-term client energy constraints, and develop a new algorithm that utilizes only currently available wireless channel information but can achieve long-term performance guarantee. Further experiments show that our algorithm results in the desired temporal client selection pattern, is adaptive to changing network environments and far outperforms benchmarks that ignore the long-term effect of FL.

READ FULL TEXT

page 18

page 21

research
05/10/2022

Client Selection and Bandwidth Allocation for Federated Learning: An Online Optimization Perspective

Federated learning (FL) can train a global model from clients' local dat...
research
04/18/2023

Joint Age-based Client Selection and Resource Allocation for Communication-Efficient Federated Learning over NOMA Networks

In federated learning (FL), distributed clients can collaboratively trai...
research
01/10/2021

Bandwidth Allocation for Multiple Federated Learning Services in Wireless Edge Networks

This paper studies a federated learning (FL) system, where multiple FL s...
research
05/31/2021

On Dynamic Resource Allocation for Blockchain Assisted Federated Learning over Wireless Channels

Blockchain assisted federated learning (BFL) has been intensively studie...
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
08/08/2022

Learning-Based Client Selection for Federated Learning Services Over Wireless Networks with Constrained Monetary Budgets

We investigate a data quality-aware dynamic client selection problem for...
research
09/18/2023

ROAR-Fed: RIS-Assisted Over-the-Air Adaptive Resource Allocation for Federated Learning

Over-the-air federated learning (OTA-FL) integrates communication and mo...

Please sign up or login with your details

Forgot password? Click here to reset