Local Graph-homomorphic Processing for Privatized Distributed Systems
Abstract
We study the generation of dependent random numbers in a distributed fashion in order to enable privatized distributed learning by networked agents. We propose a method that we refer to as local graph-homomorphic processing; it relies on the construction of particular noises over the edges to ensure a certain level of differential privacy. We show that the added noise does not affect the performance of the learned model. This is a significant improvement to previous works on differential privacy for distributed algorithms, where the noise was added in a less structured manner without respecting the graph topology and has often led to performance deterioration. We illustrate the theoretical results by considering a linear regression problem over a network of agents.
Cite
@article{arxiv.2210.15414,
title = {Local Graph-homomorphic Processing for Privatized Distributed Systems},
author = {Elsa Rizk and Stefan Vlaski and Ali H. Sayed},
journal= {arXiv preprint arXiv:2210.15414},
year = {2022}
}