Communication-Efficient Distributed Learning with Differential Privacy

TL;DR

This paper proposes a communication-efficient distributed learning algorithm that guarantees differential privacy, converges to a stationary point, and outperforms existing methods on classification tasks.

Contribution

It introduces a novel local training approach with gradient perturbation to achieve both communication efficiency and differential privacy guarantees.

Findings

Algorithm converges to a stationary point within a bounded distance.

Provides theoretical differential privacy guarantees for agents' data.

Outperforms state-of-the-art methods on classification tasks under the same privacy budget.

Abstract

We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal is achieved through a local training approach, which reduces communication frequency. The second goal is achieved by perturbing gradients during local training, specifically through gradient clipping and additive noise. We prove that the resulting algorithm converges to a stationary point of the problem within a bounded distance. Additionally, we provide theoretical privacy guarantees within a differential privacy framework that ensure agents' training data cannot be inferred from the trained model shared over the network. We show the algorithm's superior performance on a classification task under the same privacy budget, compared with state-of-the-art methods.