Exploring quantum federated learning

Nouhaila Innan, Alberto Marchisio, Mohamed Bennai, Muhammad Shafique

Abstract: Quantum federated learning (QFL) represents an emerging intersection of federated learning and quantum machine learning, designed to facilitate the training of quantum models, while preserving data privacy across decentralized networks. This chapter offers a comprehensive exploration of QFL, beginning with an examination of the foundational quantum techniques, which support the framework. It then delves into hybrid approaches, which integrate classical and quantum methods, aimed at enhancing both the scalability and efficiency of QFL. The chapter further explores the practical applications of QFL across diverse sectors, illustrating its potential to address complex, real-world challenges. Concluding with a discussion on the development and prospects of QFL, this chapter provides a holistic understanding of its role as a promising tool for the future of distributed quantum learning.

External IDs:doi:10.1016/b978-0-44-330259-6.00010-4