Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Federated Learning to Quantum Federated Learning for Space-Air-Ground Integrated Networks

Vu Khanh Quy, Nguyen Minh Quy, Tran Thi Hoai, Shaba Shaon, Md Raihan Uddin, Tien Nguyen, Dinh C. Nguyen, Aryan Kaushik, Periklis Chatzimisios

TL;DR

A few representative applications enabled by the integration of $F L$ and QFL in SAGINs are presented and a case study of QFL over UAV networks is given, showing the merit of quantum-enabled training approach over the conventional FL benchmark.

Abstract

6G wireless networks are expected to provide seamless and data-based connections that cover space-air-ground and underwater networks. As a core partition of future 6G networks, Space-Air-Ground Integrated Networks (SAGIN) have been envisioned to provide countless real-time intelligent applications. To realize this, promoting AI techniques into SAGIN is an inevitable trend. Due to the distributed and heterogeneous architecture of SAGIN, federated learning (FL) and then quantum FL are emerging AI model training techniques for enabling future privacy-enhanced and computation-efficient SAGINs. In this work, we explore the vision of using FL/QFL in SAGINs. We present a few representative applications enabled by the integration of FL and QFL in SAGINs. A case study of QFL over UAV networks is also given, showing the merit of quantum-enabled training approach over the conventional FL benchmark. Research challenges along with standardization for QFL adoption in future SAGINs are also highlighted.

From Federated Learning to Quantum Federated Learning for Space-Air-Ground Integrated Networks

TL;DR

A few representative applications enabled by the integration of and QFL in SAGINs are presented and a case study of QFL over UAV networks is given, showing the merit of quantum-enabled training approach over the conventional FL benchmark.

Abstract

6G wireless networks are expected to provide seamless and data-based connections that cover space-air-ground and underwater networks. As a core partition of future 6G networks, Space-Air-Ground Integrated Networks (SAGIN) have been envisioned to provide countless real-time intelligent applications. To realize this, promoting AI techniques into SAGIN is an inevitable trend. Due to the distributed and heterogeneous architecture of SAGIN, federated learning (FL) and then quantum FL are emerging AI model training techniques for enabling future privacy-enhanced and computation-efficient SAGINs. In this work, we explore the vision of using FL/QFL in SAGINs. We present a few representative applications enabled by the integration of FL and QFL in SAGINs. A case study of QFL over UAV networks is also given, showing the merit of quantum-enabled training approach over the conventional FL benchmark. Research challenges along with standardization for QFL adoption in future SAGINs are also highlighted.

Paper Structure

This paper contains 20 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Recent Advances in SAGINs and FL
  3. Space-Air-Ground Integrated Networks (SAGINs)
  4. Federated Learning
  5. Quantum FL
  6. Vision of Integrating FL into SAGIN
  7. Applications of FL and QFL in SAGINs
  8. FL-based SAGINs in Military Operations
  9. FL-based SAGINs in Space Applications
  10. FL-based SAGINs in Emergency Response Applications
  11. QFL in SAGINs
  12. Case Study
  13. System Model and Working Concept
  14. Parameter Setting and Simulation Results
  15. Challenges and Future Directions
  16. ...and 5 more sections

Figures (3)

  • Figure 1: An illustrated Architecture of FL-based SAGIN.
  • Figure 2: An illustrated Architecture of FL-based UAV-Ground Networks.
  • Figure 3: Comparison of QFL and FL in terms of accuracy and loss over the number of epochs.