FedOrbit：面向非独立同分布低轨卫星星座的自适应个性化联邦学习
FedOrbit: Adaptive Personalized Federated Learning for Non-IID LEO Satellite Constellations
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.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include FedOrbit, 联邦学习, 低轨卫星, 非独立同分布.
Source attribution: curated from arXiv cs.LG (@Satwat Bashir, Tasos Dagiuklas, Muddesar Iqbal).