Foundations of Quantum Federated Learning Over Classical and Quantum Networks

TL;DR

This paper explores the emerging field of quantum federated learning, combining quantum computing with federated learning over classical and quantum networks, highlighting challenges, solutions, and future research directions.

Contribution

It provides the first comprehensive analysis of QFL's challenges and opportunities, proposing novel solutions and practical recommendations for deployment.

Findings

Identified key challenges in deploying QFL over classical and quantum networks.

Developed novel solutions to address QFL-specific challenges.

Outlined promising research directions for advancing QFL.

Abstract

Quantum federated learning (QFL) is a novel framework that integrates the advantages of classical federated learning (FL) with the computational power of quantum technologies. This includes quantum computing and quantum machine learning (QML), enabling QFL to handle high-dimensional complex data. QFL can be deployed over both classical and quantum communication networks in order to benefit from information-theoretic security levels surpassing traditional FL frameworks. In this paper, we provide the first comprehensive investigation of the challenges and opportunities of QFL. We particularly examine the key components of QFL and identify the unique challenges that arise when deploying it over both classical and quantum networks. We then develop novel solutions and articulate promising research directions that can help address the identified challenges. We also provide actionable recommendations to advance the practical realization of QFL.