Federated learning has emerged as a transformative approach in machine learning, enabling multiple entities to collaboratively train models while keeping their data decentralized. This method addresses critical concerns such as data privacy and security by ensuring that sensitive information remains on local devices. Recent advancements have introduced Quantum Federated Learning (QFL), a novel paradigm that integrates quantum computing with federated learning. This fusion leverages the unique capabilities of quantum mechanics to enhance the scalability and efficiency of decentralized models. By utilizing quantum algorithms, QFL aims to process complex computations more rapidly and securely, potentially revolutionizing fields that require collaborative data analysis without compromising privacy. arxiv.org
The integration of quantum computing into federated learning presents both exciting opportunities and challenges. Quantum Federated Learning (QFL) is an emerging field that harnesses advances in Quantum Computing (QC) to improve the scalability and efficiency of decentralized Federated Learning (FL) models. This paper provides a systematic and comprehensive survey of the emerging problems and solutions when FL meets QC, from research protocol to a novel taxonomy, particularly focusing on both quantum and federated limitations, such as their architectures, Noisy Intermediate Scale Quantum (NISQ) devices, and privacy preservation. arxiv.org