Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations

2026-09-25

AI Summary

This study addresses the challenge that resource constraints in low Earth orbit (LEO) satellites hinder efficient on-orbit training in conventional federated learning. To this end, we propose COSMIC-FL, a novel framework featuring a sliced modular Mixture-of-Experts (MoE) architecture coupled with a semantic routing mechanism to achieve precise class-to-expert mapping. Furthermore, a multi-stage adaptive structured pruning strategy based on the Median Absolute Deviation (MAD) criterion is introduced to jointly optimize computational and communication overhead. Experimental results demonstrate that the proposed approach reduces energy consumption and communication volume by 80% while preserving model accuracy. Additionally, its deployment efficiency is validated on Jetson edge computing platforms, confirming practical viability for satellite-based federated learning.

Abstract

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.

Problem

• Federated Learning
• LEO Satellite Constellations
• Onboard Learning
• Resource Constraints
• Edge Computing

Innovation

• Federated Learning
• Mixture-of-Experts
• Structured Pruning
• LEO Satellite Constellations
• Onboard Learning