Empowering the Edge Intelligence by Air-Ground Integrated Federated Learning

TL;DR

The paper addresses the challenge of delivering ubiquitous edge intelligence in 6G by proposing AGIFL, a framework that fuses federated learning with air-ground integrated networks and on-demand UAV deployment. It delineates four forms of AGIFL (A2A, G2A, A2G, Mixed) and discusses learning-oriented deployment, resource allocation, and data/control management as key technical challenges. A case study on G2A FL demonstrates how UAV hovering location impacts learning performance, energy consumption, and latency, underscoring the importance of optimized aerial deployment. The work offers a roadmap for enabling privacy-preserving, scalable edge learning across three-dimensional networks and highlights future directions, including security enhancements and decentralized architectures, to advance practical deployment in 6G systems.

Abstract

Ubiquitous intelligence has been widely recognized as a critical vision of the future sixth generation (6G) networks, which implies the intelligence over the whole network from the core to the edge including end devices. Nevertheless, fulfilling such vision, particularly the intelligence at the edge, is extremely challenging, due to the limited resources of edge devices as well as the ubiquitous coverage envisioned by 6G. To empower the edge intelligence, in this article, we propose a novel framework called AGIFL (Air-Ground Integrated Federated Learning), which organically integrates air-ground integrated networks and federated learning (FL). In the AGIFL, leveraging the flexible on-demand 3D deployment of aerial nodes such as unmanned aerial vehicles (UAVs), all the nodes can collaboratively train an effective learning model by FL. We also conduct a case study to evaluate the effect of two different deployment schemes of the UAV over the learning and network performance. Last but not the least, we highlight several technical challenges and future research directions in the AGIFL.

Figures (5)

• Figure 1: An illustration of FedAvg CELD.
• Figure 2: Different forms of federated learning in AGIFL.
• Figure 3: Energy consumption vs. training rounds.
• Figure 4: Testing accuracy vs. UAV's energy budget.
• Figure 5: Training latency vs. training rounds.