A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks
This work addresses resource constraints in satellite networks for Earth observation and sensing, offering incremental improvements in federated learning efficiency.
The paper tackles the challenge of achieving reliable convergence while minimizing processing time and energy consumption in heterogeneous and partially unlabeled Low Earth Orbit satellite networks for 6G applications, proposing a semi-supervised federated learning framework with hierarchical clustering aggregation that reduces processing time up to 3x and energy consumption up to 4x compared to other methods while maintaining model accuracy.
Low Earth Orbit (LEO) satellites are emerging as key components of 6G networks, with many already deployed to support large-scale Earth observation and sensing related tasks. Federated Learning (FL) presents a promising paradigm for enabling distributed intelligence in these resource-constrained and dynamic environments. However, achieving reliable convergence, while minimizing both processing time and energy consumption, remains a substantial challenge, particularly in heterogeneous and partially unlabeled satellite networks. To address this challenge, we propose a novel semi-supervised federated learning framework tailored for LEO satellite networks with hierarchical clustering aggregation. To further reduce communication overhead, we integrate sparsification and adaptive weight quantization techniques. In addition, we divide the FL clustering into two stages: satellite cluster aggregation stage and Ground Stations (GSs) aggregation stage. The supervised learning at GSs guides selected Parameter Server (PS) satellites, which in turn support fully unlabeled satellites during the federated training process. Extensive experiments conducted on a satellite network testbed demonstrate that our proposal can significantly reduce processing time (up to 3x) and energy consumption (up to 4x) compared to other comparative methods while maintaining model accuracy.