no code implementations • 12 Jun 2021 • Madhusanka Manimel Wadu, Sumudu Samarakoon, Mehdi Bennis
In this article we investigate the problem of client scheduling and resource block (RB) allocation to enhance the performance of model training using FL, over a pre-defined training duration under imperfect channel state information (CSI) and limited local computing resources.
no code implementations • 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).
Networking and Internet Architecture