EUVIMEDEUVIMED entdecken
Crossref

Transitioning From Federated Learning to Quantum Federated Learning in Internet of Things: A Comprehensive Survey

Cheng Qiao, Mianjie Li, Yuan Liu, Zhihong Tian

IEEE Communications Surveys & Tutorials · 2025-02 · 27 (1) · 509-545

DOI: 10.1109/comst.2024.3399612 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Communications Surveys & Tutorials, 2025-02. Verfasst von Cheng Qiao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 88-mal zitiert (Crossref) und nennt 343 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantum Federated Learning (QFL) recently becomes a promising approach with the potential to revolutionize Machine Learning (ML). It merges the established strengths of classical Federated Learning (FL) with the exceptional parallel mechanism and exponential speed enhancements characteristic of quantum computing. While this innovative fusion has garnered considerable attention, a notable gap in current research is the tendency to consider traditional FL and its quantum-enhanced counterpart, QFL, in isolation. This approach often overlooks the critical role of Quantum Machine Learning (QML) in effectively bridging these two domains. Recognizing this, there emerges a pressing need for a comprehensive survey that encompasses the entire spectrum of FL paradigms, from foundational FL concepts to the cutting-edge developments in QFL. Our survey aims to address this need by providing an in-depth exploration of the various facets of FL paradigms, ultimately leading to a thorough understanding of Quantum Federated Learning. We start by emphasizing the driving factors and prevalent research topics related to FL. To develop a more efficient, robust, and precise computing paradigm, we investigate the current solutions that address the concerns of heterogeneity, privacy, security, and evaluation in FL. After that, we explore the possibility of improving the computational efficiency of ML methods by leveraging the computational capabilities of quantum computers. In particular, we discuss the frameworks, evaluation, and applications for QML. Following that, we detail the integration of quantum computing technologies with standard FL, aiming to bolster computational performance and mitigate security and privacy risks. The potential solutions to improve the efficiency (i.e., slimming mechanism) and respect the privacy and security (i.e., quantum key distribution) for QFL are explored. Finally, we outline some critical future directions towards unlocking the full potential of QFL in distributed machine learning.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Basic Research Program Cofunded by Guangzhou City and Guangzhou University
  • Joint Research Fund of Guangzhou and University
  • Guangdong Higher Education Innovation Group

Zitieren

APA

Qiao, C., Li, M., Liu, Y., & Tian, Z. (2025). Transitioning From Federated Learning to Quantum Federated Learning in Internet of Things: A Comprehensive Survey. IEEE Communications Surveys & Tutorials, 27(1), 509-545. https://doi.org/10.1109/comst.2024.3399612

Vancouver

Qiao C, Li M, Liu Y, Tian Z. Transitioning From Federated Learning to Quantum Federated Learning in Internet of Things: A Comprehensive Survey. IEEE Communications Surveys & Tutorials. 2025;27(1):509-545. doi:10.1109/comst.2024.3399612

BibTeX
@article{Qiao2025,
  author = {Qiao, Cheng and Li, Mianjie and Liu, Yuan and Tian, Zhihong},
  title = {Transitioning From Federated Learning to Quantum Federated Learning in Internet of Things: A Comprehensive Survey},
  journal = {IEEE Communications Surveys & Tutorials},
  year = {2025},
  volume = {27},
  number = {1},
  pages = {509--545},
  doi = {10.1109/comst.2024.3399612}
}
Kostenlos starten →