Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation

TL;DR

This paper introduces a privacy-preserving federated learning scheme using over-the-air computation with dynamic power control, enhancing model accuracy and robustness against synchronization errors, fading, and noise.

Contribution

It proposes a novel dynamic power control algorithm for over-the-air federated learning that improves privacy and performance over existing methods.

Findings

Mitigates impact of synchronization errors, fading, and noise

Provides theoretical convergence proof

Enhances privacy and model accuracy

Abstract

To further preserve model weight privacy and improve model performance in Federated Learning (FL), FL via Over-the-Air Computation (AirComp) scheme based on dynamic power control is proposed. The edge devices (EDs) transmit the signs of local stochastic gradients by activating two adjacent orthogonal frequency division multi-plexing (OFDM) subcarriers, and majority votes (MVs) at the edge server (ES) are obtained by exploiting the energy accumulation on the subcarriers. Then, we propose a dynamic power control algorithm to further offset the biased aggregation of the MV aggregation values. We show that the whole scheme can mitigate the impact of the time synchronization error, channel fading and noise. The theoretical convergence proof of the scheme is re-derived.