传统的联邦学习（FL）框架高度依赖地面网络通信，而地面通信基础设施的覆盖限制以及日益加剧的带宽拥塞显著阻碍了FL训练的收敛。幸运的是，低轨卫星（LEO）网络提供全球范围接入，为传统地面通信架构下的联邦学习系统提供了具有前景的通信辅助方案。然而，相对受限的星地通信带宽，以及联邦学习设备在数据、带宽和计算能力等方面的异构性，仍然对实现高效且鲁棒的卫星辅助联邦学习系统带来了巨大挑战。为应对上述挑战，我们提出了 SatFed，一种资源高效的低轨卫星辅助异构联邦学习框架。SatFed 引入基于新鲜度的模型优先级队列来优化带宽受限条件下的星地通信资源利用效率，确保联邦学习系统中的关键模型被优先传输。此外，SatFed 通过构建一个多重图，实时地捕捉设备间的异构性关系——包括数据分布、地面带宽以及算力资源。该多重图使 SatFed 能够将通过低轨卫星网络传输的模型更新聚合为参与 FL 训练的设备间的对等指导，从而提升异构环境下的本地训练效果。在真实低轨卫星网络上的大量实验表明，SatFed 相较于最先进的基准方法，在性能和鲁棒性方面均表现优越。

Traditional federated learning (FL) frameworks rely heavily on terrestrial networks, whose coverage limitations and increasing bandwidth congestion significantly hinder model convergence. Fortunately, the advancement of low-Earth-orbit (LEO) satellite networks offers promising new communication avenues to augment traditional terrestrial FL. Despite this potential, the limited satellite–ground communication bandwidth and the heterogeneous operating environments of ground devices—including variations in data, bandwidth, and computing power—pose substantial challenges for effective and robust satellite-assisted FL. To address these challenges, we propose SatFed, a resource-efficient satellite-assisted heterogeneous FL framework. SatFed implements freshness-based model-prioritization queues to optimize the use of highly constrained satellite–ground bandwidth, ensuring the transmission of the most critical models. Additionally, a multigraph is constructed to capture the real-time heterogeneous relationships between devices, including data distribution, terrestrial bandwidth, and computing capability. This multigraph enables SatFed to aggregate satellite-transmitted models into peer guidance, improving local training in heterogeneous environments. Extensive experiments with real-world LEO satellite networks demonstrate that SatFed achieves superior performance and robustness compared with state-of-the-art benchmarks.