FLUE: Federated Learning with Un-Encrypted model weights

TL;DR

This paper proposes a new federated learning approach that enhances privacy by using coded local gradients and coded proxies, eliminating the need for encryption while maintaining effective model training.

Contribution

It introduces a novel federated learning algorithm leveraging coded gradients and proxies, with two implementation variants and demonstrated convergence without encryption.

Findings

Effective convergence demonstrated in simulations

Enhanced privacy through coding and noise injection

Flexible algorithms adaptable to data and coding schemes

Abstract

Federated Learning enables diverse devices to collaboratively train a shared model while keeping training data locally stored, avoiding the need for centralized cloud storage. Despite existing privacy measures, concerns arise from potential reverse engineering of gradients, even with added noise, revealing private data. To address this, recent research emphasizes using encrypted model parameters during training. This paper introduces a novel federated learning algorithm, leveraging coded local gradients without encryption, exchanging coded proxies for model parameters, and injecting surplus noise for enhanced privacy. Two algorithm variants are presented, showcasing convergence and learning rates adaptable to coding schemes and raw data characteristics. Two encryption-free implementations with fixed and random coding matrices are provided, demonstrating promising simulation results from both federated optimization and machine learning perspectives.