Momentum Gradient Descent Federated Learning with Local Differential Privacy

TL;DR

This paper proposes a novel federated learning approach that combines momentum gradient descent with local differential privacy to enhance privacy guarantees and model performance in distributed data environments.

Contribution

It introduces a new method integrating federated learning, local differential privacy, and momentum gradient descent to address privacy and efficiency challenges.

Findings

Improved privacy preservation in federated learning.

Enhanced model accuracy with the proposed method.

Reduced communication costs in distributed training.

Abstract

Nowadays, the development of information technology is growing rapidly. In the big data era, the privacy of personal information has been more pronounced. The major challenge is to find a way to guarantee that sensitive personal information is not disclosed while data is published and analyzed. Centralized differential privacy is established on the assumption of a trusted third-party data curator. However, this assumption is not always true in reality. As a new privacy preservation model, local differential privacy has relatively strong privacy guarantees. Although federated learning has relatively been a privacy-preserving approach for distributed learning, it still introduces various privacy concerns. To avoid privacy threats and reduce communication costs, in this article, we propose integrating federated learning and local differential privacy with momentum gradient descent to improve the performance of machine learning models.