卫星联邦学习老被轨道数据不均衡坑，FedOrbit 用分层聚合和自适应分解，在遥感基准上最高提了 16 个点，做边缘 AI 的可以看看。
FedOrbit 针对低轨卫星星座中非独立同分布数据和地面站可见性不规则问题，提出结合轨道级训练、类感知分层聚合、质量加权特征聚合及自适应特征分解的方法。在三个遥感基准和两种非独立同分布划分下，FedOrbit 在六种设置中五种取得最高准确率，第六种与最佳结果相差 0.9 个百分点。相比最强基线，在 Dirichlet 划分下提升 16.1 个百分点，在病态划分下提升 8.6 个百分点，且在六种设置中五种具有最小的轨道间准确率差异。
FedOrbit: Adaptive Personalized Federated Learning for Non-IID LEO Satellite Constellations
Federated learning (FL) in Low Earth Orbit (LEO) satellite constellations is affected by non-IID data and irregular ground-station visibility, both driven by orbital geometry. Global aggregation performs poorly when orbit-level class distributions are disjoint, while strong personalisation can be excessive when these distributions overlap. We present FedOrbit, which combines continuous orbit-level training over inter-satellite links, class-aware hierarchical aggregation, quality-weighted feature aggregation with return-rate dampening, and adaptive feature decomposition based on inter-orbit class similarity. Across three remote-sensing benchmarks and two non-IID partitions, FedOrbit achieves the highest accuracy in five of six settings and is within $0.9$ percentage points of the best result in the sixth. The gains over the strongest baseline reach $16.1$ percentage points under Dirichlet partitioning and $8.6$ under pathological partitioning, with the smallest per-orbit accuracy spread in five of six settings.