Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning

TL;DR

This paper introduces A-FADMM, a wireless federated learning framework that leverages channel perturbations and over-the-air aggregation to enhance privacy, reduce bandwidth, and improve scalability, with proven convergence and privacy guarantees.

Contribution

It proposes a novel analog federated ADMM algorithm that uses wireless channel properties for privacy and efficiency, addressing key challenges in scalable federated learning.

Findings

A-FADMM achieves convergence under time-varying channels.

The framework enhances privacy by obscuring individual model updates.

It improves bandwidth efficiency and scalability in wireless federated learning.

Abstract

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker's model update while multiple workers' updates incur significant interference under limited bandwidth. To address these challenges, in this work we formulate a novel constrained optimization problem, and propose an FL framework harnessing wireless channel perturbations and interference for improving privacy, bandwidth-efficiency, and scalability. The resultant algorithm is coined analog federated ADMM (A-FADMM) based on analog transmissions and the alternating direction method of multipliers (ADMM). In A-FADMM, all workers upload their model updates to the parameter server (PS) using a single channel via analog transmissions, during which all models are perturbed and aggregated over-the-air. This not only saves communication bandwidth, but also hides each worker's exact model update trajectory from any eavesdropper including the honest-but-curious PS, thereby preserving data privacy against model inversion attacks. We formally prove the convergence and privacy guarantees of A-FADMM for convex functions under time-varying channels, and numerically show the effectiveness of A-FADMM under noisy channels and stochastic non-convex functions, in terms of convergence speed and scalability, as well as communication bandwidth and energy efficiency.