SPARK: A Scalable Peer-to-Peer Asynchronous Resilient Framework for Federated Learning in Non-Terrestrial Networks
Guangsheng Yu, Ying He, Eryk Dutkiewicz, Bathiya Senanayake, Manik Attygalle · IEEE Transactions on Machine Learning in Communications and Networking · 2025
Federated Learning (FL) faces significant challenges when applied in 6G (sixth-generation wireless technology) Non-Terrestrial Network (NTN) environments, including heterogeneous interference, stringent requirements for real-time model responsiveness, and limited ability to collect comprehensive datasets due to the absence of a global network view. In this paper, we propose SPARK, a novel framework designed to enable a fully decentralized FL process tailored for NTN. By leveraging a Directed acyclic graph (DAG)-based architecture, SPARK addresses the unique demands of NTN through asynchronous updates, localized learning prioritization, and adaptive aggregation strategies, ensuring robust performance under dynamic and constrained conditions. Extensive experiments demonstrate that SPARK outperforms other FL frameworks and effectively addresses the key challenges of NTN-based FL through its asynchronous design–ensuringresilienceunder communication delays, enhancingresponsivenessvia timely local updates, and improvingcoveragethrough altitude-aware aggregation that leverages diverse, high-altitude knowledge.