A Demonstration of Over-the-Air Computation for Federated Edge Learning

TL;DR

This paper demonstrates over-the-air computation for federated edge learning using synchronized SDRs, achieving high accuracy without channel state information, and introduces a novel synchronization method for precise timing.

Contribution

It presents a new synchronization technique for SDRs enabling over-the-air federated learning without channel state information.

Findings

Test accuracy exceeds 95% for various data distributions

Synchronization method works with low-cost SDRs

Over-the-air computation is feasible without channel state info

Abstract

In this study, we propose a general-purpose synchronization method that allows a set of software-defined radios (SDRs) to transmit or receive any in-phase/quadrature data with precise timings while maintaining the baseband processing in the corresponding companion computers. The proposed method relies on the detection of a synchronization waveform in both receive and transmit directions and controlling the direct memory access blocks jointly with the processing system. By implementing this synchronization method on a set of low-cost SDRs, we demonstrate the performance of frequency-shift keying (FSK)-based majority vote (MV), i.e., an over-the-air computation scheme for federated edge learning, and introduce the corresponding procedures. Our experiment shows that the test accuracy can reach more than 95% for homogeneous and heterogeneous data distributions without using channel state information at the edge devices.