资源感知的联邦混合专家模型与自适应剪枝：用于低地球轨道卫星星座的星上学习
Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations
浏览论文内容
中文总结 AI 辅助
提出COSMIC-FL框架，通过混合专家架构与自适应剪枝，在资源受限的LEO卫星上实现高效联邦学习，降低通信计算能耗达80%。
中文摘要 AI 辅助
低地球轨道（LEO）卫星越来越多地被期望执行星上学习，以支持诸如灾害响应和环境监测等应用。然而，传统的联邦学习（FL）并不适用于星上卫星学习，因为它假设的计算、内存和通信资源超出了资源受限的LEO平台的能力，通常需要将原始图像传输到地面站。我们提出了COSMIC-FL，一个资源感知的联邦学习框架，用于在LEO卫星星座中实现高效的星上学习。COSMIC-FL引入了两种互补的混合专家（MoE）架构：一种切片设计，共享骨干表示同时激活任务特定的通道子集；以及一种模块化设计，采用轻量级门控将输入路由到物理分离的专家网络。语义类别到专家的映射使每颗卫星能够仅训练、更新和通信与其本地数据相关的专家路径。为了进一步提高效率，COSMIC-FL集成了分阶段优化与三种结构化剪枝策略：服务器端剪枝、客户端端固定比例剪枝与均值投票聚合，以及基于聚合重要性和基于MAD的差距准则的自适应客户端逐层剪枝。结合语义专家路由，这些技术共同调整计算和模型稀疏性以适应数据语义和层重要性，为异构空间平台产生了有利的精度-效率权衡。在高度非独立同分布设置下的六个图像分类基准上的实验表明，COSMIC-FL在保持竞争性精度的同时，将通信、计算和能量消耗相比最先进的联邦学习方法降低了高达80%。我们进一步在NVIDIA Jetson AGX Orin上验证了COSMIC-FL，确认了其在现实嵌入式部署约束下的效率提升。
英文摘要
Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental monitoring. However, conventional federated learning (FL) is ill-suited to onboard satellite learning, as it assumes computational, memory, and communication resources beyond the capabilities of resource-constrained LEO platforms, often necessitating the transmission of raw imagery to ground stations. We present COSMIC-FL, a resource-aware FL framework for efficient onboard learning in LEO satellite constellations. COSMIC-FL introduces two complementary Mixture-of-Experts (MoE) architectures: a Sliced design that shares backbone representations while activating task-specific channel subsets, and a Modular design that employs lightweight gating to route inputs to physically separated expert networks. A semantic class-to-expert mapping enables each satellite to train, update, and communicate only the expert paths relevant to its local data. To further improve efficiency, COSMIC-FL integrates staged optimization with three structured pruning strategies: server-side pruning, client-side fixed-ratio pruning with mean-vote aggregation, and adaptive client-side per-layer pruning based on aggregated importance and a MAD-based gap criterion. Combined with semantic expert routing, these techniques jointly adapt computation and model sparsity to both data semantics and layer importance, yielding a favourable accuracy--efficiency trade-off for heterogeneous space platforms. Experiments on six image classification benchmarks under highly non-i.i.d. settings show that COSMIC-FL maintains competitive accuracy while reducing communication, computation, and energy consumption by up to 80% over SOTA FL methods. We further validate COSMIC-FL on an NVIDIA Jetson AGX Orin, confirming its efficiency gains under realistic embedded deployment constraints.
