Device Association and Resource Allocation for Hierarchical Split Federated Learning in Space-Air-Ground Integrated Network

TL;DR

This work addresses Federated Learning in Space-Air-Ground Integrated Networks (SAGIN) where devices are resource-constrained and data are non-IID. It introduces Hierarchical Split Federated Learning (HSFL) and derives a convergence bound, formulating a joint optimization of split layer $ ext{ell}$, device association, and resource allocation to minimize a weighted sum of latency and loss. The solution decomposes into bandwidth and computation allocation (with closed-form results for bandwidth via Theorem 2 and KKT-based resource allocation for compute) and a primal-dual device-association step, including an exhaustive search over split layers. Simulation on CIFAR-10 with AlexNet demonstrates that HSFL achieves higher test accuracy and lower training latency than baselines, highlighting the benefits of SFL in SAGIN for remote-edge intelligent deployments.

Abstract

6G facilitates deployment of Federated Learning (FL) in the Space-Air-Ground Integrated Network (SAGIN), yet FL confronts challenges such as resource constrained and unbalanced data distribution. To address these issues, this paper proposes a Hierarchical Split Federated Learning (HSFL) framework and derives its upper bound of loss function. To minimize the weighted sum of training loss and latency, we formulate a joint optimization problem that integrates device association, model split layer selection, and resource allocation. We decompose the original problem into several subproblems, where an iterative optimization algorithm for device association and resource allocation based on brute-force split point search is proposed. Simulation results demonstrate that the proposed algorithm can effectively balance training efficiency and model accuracy for FL in SAGIN.

Figures (3)

• Figure 1: Learning performance of AlexNet on CIFAR-10
• Figure 2: The impact of bandwidth
• Figure 3: The impact of UAV computing capability