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

3 Feb 2020  ·  Madhusanka Manimel Wadu, Sumudu Samarakoon, Mehdi Bennis ·

In this work, we propose a novel joint client scheduling and resource block (RB) allocation policy to minimize the loss of accuracy in federated learning (FL) over wireless compared to a centralized training-based solution, under imperfect channel state information (CSI). First, the problem is cast as a stochastic optimization problem over a predefined training duration and solved using the Lyapunov optimization framework. In order to learn and track the wireless channel, a Gaussian process regression (GPR)-based channel prediction method is leveraged and incorporated into the scheduling decision. The proposed scheduling policies are evaluated via numerical simulations, under both perfect and imperfect CSI. Results show that the proposed method reduces the loss of accuracy up to 25.8% compared to state-of-the-art client scheduling and RB allocation methods.

PDF Abstract
No code implementations yet. Submit your code now

Categories


Networking and Internet Architecture

Datasets


  Add Datasets introduced or used in this paper