Decentralized Wireless Federated Learning with Differential Privacy

TL;DR

This paper introduces DWFL, a decentralized wireless federated learning algorithm that enhances privacy, fault tolerance, and communication efficiency in IoT networks, matching centralized convergence rates and demonstrating strong empirical performance.

Contribution

The paper proposes DWFL, a novel decentralized wireless federated learning algorithm that ensures differential privacy and achieves convergence rates comparable to centralized methods.

Findings

DWFL satisfies $(,)$-differential privacy.

Privacy budget per worker scales as $\u221a{1/N}$, improving over orthogonal transmission.

DWFL converges at rate $(rac{1}{TN})$, matching centralized algorithms.

Abstract

This paper studies decentralized federated learning algorithms in wireless IoT networks. The traditional parameter server architecture for federated learning faces some problems such as low fault tolerance, large communication overhead and inaccessibility of private data. To solve these problems, we propose a Decentralized-Wireless-Federated-Learning algorithm called DWFL. The algorithm works in a system where the workers are organized in a peer-to-peer and server-less manner, and the workers exchange their privacy preserving data with the analog transmission scheme over wireless channels in parallel. With rigorous analysis, we show that DWFL satisfies $(\epsilon,\delta)$-differential privacy and the privacy budget per worker scales as $\mathcal{O}(\frac{1}{\sqrt{N}})$, in contrast with the constant budget in the orthogonal transmission approach. Furthermore, DWFL converges at the same rate of $\mathcal{O}(\sqrt{\frac{1}{TN}})$ as the best known centralized algorithm with a central parameter server. Extensive experiments demonstrate that our algorithm DWFL also performs well in real settings.