A Graph Federated Architecture with Privacy Preserving Learning

TL;DR

This paper introduces a privacy-preserving multi-server federated learning architecture called graph federated learning, which uses cryptography and differential privacy to protect sensitive data while maintaining performance.

Contribution

It develops a novel multi-server federated learning scheme that incorporates privacy-preserving techniques within a graph structure, addressing server sensitivity and privacy concerns.

Findings

Privatized learning performance matches non-private algorithms under certain conditions.

The scheme is robust to increased noise variance in privacy mechanisms.

The approach extends federated learning to a graph-based multi-server setting.

Abstract

Federated learning involves a central processor that works with multiple agents to find a global model. The process consists of repeatedly exchanging estimates, which results in the diffusion of information pertaining to the local private data. Such a scheme can be inconvenient when dealing with sensitive data, and therefore, there is a need for the privatization of the algorithms. Furthermore, the current architecture of a server connected to multiple clients is highly sensitive to communication failures and computational overloads at the server. Thus in this work, we develop a private multi-server federated learning scheme, which we call graph federated learning. We use cryptographic and differential privacy concepts to privatize the federated learning algorithm that we extend to the graph structure. We study the effect of privatization on the performance of the learning algorithm for general private schemes that can be modeled as additive noise. We show under convexity and Lipschitz conditions, that the privatized process matches the performance of the non-private algorithm, even when we increase the noise variance.