Metraipolis › archive › dc_8a6671eef272

Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations — arXiv:2609.31932

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31932
License (as archived)
CC0-1.0
Archived
2026-10-07T22:36:07.872Z
SHA-256 of the archived text
6ff5567661a542e68ed4f1c3dcacea72f28d560fea620cdb16b022817ea120fd
Stable URL of this page
https://metraipolis.com/documento/dc_8a6671eef272

How to cite

Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations — arXiv:2609.31932 — arXiv (en), https://arxiv.org/abs/2609.31932 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a6671eef272 (Metraipolis archive dc_8a6671eef272, sha256 6ff5567661a542e68ed4f1c3dcacea72f28d560fea620cdb16b022817ea120fd)
BibTeX
@misc{dc8a6671eef272,
  title = {Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations — arXiv:2609.31932},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31932},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a6671eef272; sha256 6ff5567661a542e68ed4f1c3dcacea72f28d560fea620cdb16b022817ea120fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31932. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.31932 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:27.552Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).