Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach

TL;DR

This paper introduces SDM-DSGD, a decentralized stochastic gradient method that significantly enhances privacy and communication efficiency in wireless edge learning, backed by theoretical guarantees and extensive experiments.

Contribution

The paper proposes a novel SDM-DSGD algorithm that improves privacy and communication efficiency in distributed edge learning, with theoretical analysis and practical guidelines.

Findings

Outperforms existing methods in privacy and communication efficiency

Improves training-privacy trade-off by two orders of magnitude

Validated through experiments on MNIST and CIFAR-10 datasets

Abstract

With rise of machine learning (ML) and the proliferation of smart mobile devices, recent years have witnessed a surge of interest in performing ML in wireless edge networks. In this paper, we consider the problem of jointly improving data privacy and communication efficiency of distributed edge learning, both of which are critical performance metrics in wireless edge network computing. Toward this end, we propose a new decentralized stochastic gradient method with sparse differential Gaussian-masked stochastic gradients (SDM-DSGD) for non-convex distributed edge learning. Our main contributions are three-fold: i) We theoretically establish the privacy and communication efficiency performance guarantee of our SDM-DSGD method, which outperforms all existing works; ii) We show that SDM-DSGD improves the fundamental training-privacy trade-off by {\em two orders of magnitude} compared with the state-of-the-art. iii) We reveal theoretical insights and offer practical design guidelines for the interactions between privacy preservation and communication efficiency, two conflicting performance goals. We conduct extensive experiments with a variety of learning models on MNIST and CIFAR-10 datasets to verify our theoretical findings. Collectively, our results contribute to the theory and algorithm design for distributed edge learning.