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

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.

References in corpus (10)

• Deep Learning with Differential Privacy
• Renyi Differential Privacy
• Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization
• Communication Compression for Decentralized Training
• An Exact Quantized Decentralized Gradient Descent Algorithm
• Subsampled Rényi Differential Privacy and Analytical Moments Accountant
• DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM
• LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning
• Efficient Private ERM for Smooth Objectives
• Robust and Communication-Efficient Collaborative Learning

Cited by in corpus (2)

• Influence Function based Data Poisoning Attacks to Top-N Recommender Systems
• CFedAvg: Achieving Efficient Communication and Fast Convergence in Non-IID Federated Learning