Multi-cell Non-coherent Over-the-Air Computation for Federated Edge Learning

TL;DR

This paper introduces a multi-cell over-the-air computation framework for federated edge learning that eliminates the need for channel state information and synchronization, improving scalability and latency.

Contribution

It proposes a non-coherent FSK-based majority vote scheme for multi-cell FEEL, enabling interference exploitation and convergence proof.

Findings

Effective in multi-cell scenarios with improved test accuracy

Eliminates CSI requirement at edge devices and servers

Proven convergence of the non-convex optimization problem

Abstract

In this paper, we propose a framework where over-the-air computation (OAC) occurs in both uplink (UL) and downlink (DL), sequentially, in a multi-cell environment to address the latency and the scalability issues of federated edge learning (FEEL). To eliminate the channel state information (CSI) at the edge devices (EDs) and edge servers (ESs) and relax the time-synchronization requirement for the OAC, we use a non-coherent computation scheme, i.e., frequency-shift keying (FSK)-based majority vote (MV) (FSK-MV). With the proposed framework, multiple ESs function as the aggregation nodes in the UL and each ES determines the MVs independently. After the ESs broadcast the detected MVs, the EDs determine the sign of the gradient through another OAC in the DL. Hence, inter-cell interference is exploited for the OAC. In this study, we prove the convergence of the non-convex optimization problem for the FEEL with the proposed OAC framework. We also numerically evaluate the efficacy of the proposed method by comparing the test accuracy in both multi-cell and single-cell scenarios for both homogeneous and heterogeneous data distributions.