Enhancing Privacy in Federated Learning through Local Training

TL;DR

This paper introduces Fed-PLT, a federated learning algorithm that reduces communication costs and enhances privacy by combining local training with differential privacy analysis, maintaining accuracy and offering solver flexibility.

Contribution

The paper proposes Fed-PLT, a novel federated learning method that reduces communication and improves privacy without sacrificing accuracy, allowing flexible local training solvers.

Findings

Fed-PLT reduces communication rounds significantly.

Local training does not impact model accuracy.

Differential privacy bounds depend on local training epochs.

Abstract

In this paper we propose the federated learning algorithm Fed-PLT to overcome the challenges of (i) expensive communications and (ii) privacy preservation. We address (i) by allowing for both partial participation and local training, which significantly reduce the number of communication rounds between the central coordinator and computing agents. The algorithm matches the state of the art in the sense that the use of local training demonstrably does not impact accuracy. Additionally, agents have the flexibility to choose from various local training solvers, such as (stochastic) gradient descent and accelerated gradient descent. Further, we investigate how employing local training can enhance privacy, addressing point (ii). In particular, we derive differential privacy bounds and highlight their dependence on the number of local training epochs. We assess the effectiveness of the proposed algorithm by comparing it to alternative techniques, considering both theoretical analysis and numerical results from a classification task.