Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph

TL;DR

This paper introduces a novel decentralized federated learning algorithm that ensures privacy and adapts to changing communication networks using consensus, secret sharing, and the Metropolis-Hastings method.

Contribution

It presents the first privacy-preserving decentralized federated learning algorithm capable of handling dynamic communication graphs with theoretical correctness and privacy guarantees.

Findings

Algorithm achieves privacy-preserving global model consensus.

Effective in high-mobility, time-varying communication environments.

Simulation results demonstrate computational efficiency on real-world datasets.

Abstract

Establishing how a set of learners can provide privacy-preserving federated learning in a fully decentralized (peer-to-peer, no coordinator) manner is an open problem. We propose the first privacy-preserving consensus-based algorithm for the distributed learners to achieve decentralized global model aggregation in an environment of high mobility, where the communication graph between the learners may vary between successive rounds of model aggregation. In particular, in each round of global model aggregation, the Metropolis-Hastings method is applied to update the weighted adjacency matrix based on the current communication topology. In addition, the Shamir's secret sharing scheme is integrated to facilitate privacy in reaching consensus of the global model. The paper establishes the correctness and privacy properties of the proposed algorithm. The computational efficiency is evaluated by a simulation built on a federated learning framework with a real-word dataset.