Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach
This work addresses critical performance metrics for machine learning in wireless edge networks, offering a novel solution that is incremental in combining privacy and efficiency enhancements.
The paper tackles the problem of improving both data privacy and communication efficiency in distributed edge learning by proposing a new decentralized stochastic gradient method with sparse differential Gaussian-masked gradients (SDM-DSGD), achieving a two-orders-of-magnitude improvement in the training-privacy trade-off compared to state-of-the-art methods.
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.