Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation

TL;DR

This paper introduces a high-precision over-the-air computation method for federated learning that enhances spectrum and energy efficiency, enabling mobile devices to collaboratively train models with reduced resource consumption.

Contribution

It proposes a novel multi-bit over-the-air computation scheme with high-precision digital modulation and an energy-efficient FL design optimized through convergence analysis.

Findings

Outperforms existing schemes in spectrum utilization

Reduces energy consumption in mobile FL devices

Maintains high learning accuracy

Abstract

Federated learning (FL) enables mobile devices to collaboratively learn a shared prediction model while keeping data locally. However, there are two major research challenges to practically deploy FL over mobile devices: (i) frequent wireless updates of huge size gradients v.s. limited spectrum resources, and (ii) energy-hungry FL communication and local computing during training v.s. battery-constrained mobile devices. To address those challenges, in this paper, we propose a novel multi-bit over-the-air computation (M-AirComp) approach for spectrum-efficient aggregation of local model updates in FL and further present an energy-efficient FL design for mobile devices. Specifically, a high-precision digital modulation scheme is designed and incorporated in the M-AirComp, allowing mobile devices to upload model updates at the selected positions simultaneously in the multi-access channel. Moreover, we theoretically analyze the convergence property of our FL algorithm. Guided by FL convergence analysis, we formulate a joint transmission probability and local computing control optimization, aiming to minimize the overall energy consumption (i.e., iterative local computing + multi-round communications) of mobile devices in FL. Extensive simulation results show that our proposed scheme outperforms existing ones in terms of spectrum utilization, energy efficiency, and learning accuracy.