mlsanityData to 7 Oct 2026

On-Board Federated Learning for Dense LEO Constellations

arXiv 2111.12769 ↗First posted 24 Nov 2021eess.SPcited by 22

Not on the map. Why?

Abstract (arXiv)

Mega-constellations of small-size Low Earth Orbit (LEO) satellites are currently planned and deployed by various private and public entities. While global connectivity is the main rationale, these constellations also offer the potential to gather immense amounts of data, e.g., for Earth observation. Power and bandwidth constraints together with motives like privacy, limiting delay, or resiliency make it desirable to process this data directly within the constellation. We consider the implementation of on-board federated learning (FL) orchestrated by an out-of-constellation parameter server (PS) and propose a novel communication scheme tailored to support FL. It leverages intra-orbit inter-satellite links, the predictability of satellite movements and partial aggregating to massively reduce the training time and communication costs. In particular, for a constellation with 40 satellites equally distributed among five low Earth orbits and the PS in medium Earth orbit, we observe a 29x speed-up in the training process time and a 8x traffic reduction at the PS over the baseline.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Nov 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 6; 2024: 8; 2025: 1; 2026: 2.

22 papers.

Sort:

  1. 2022FedHAP: Fast Federated Learning for LEO Constellations Using Collaborative HAPscited by 21
  2. 2022Federated Learning in Satellite Constellationscited by 21
  3. 2022AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platformscited by 18
  4. 2023Optimizing Federated Learning in LEO Satellite Constellations via Intra-Plane Model Propagation and Sink Satellite Schedulingcited by 10
  5. 2024Satellite Federated Edge Learning: Architecture Design and Convergence Analysiscited by 10
  6. 2023One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutescited by 7
  7. 2023Edge Selection and Clustering for Federated Learning in Optical Inter-LEO Satellite Constellationcited by 6
  8. 2023Secure and Efficient Federated Learning in LEO Constellations using Decentralized Key Generation and On-Orbit Model Aggregationcited by 6
  9. 2024Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDMcited by 6
  10. 2022Selected Trends in Artificial Intelligence for Space Applicationscited by 5
  11. 2023Cooperative Federated Learning over Ground-to-Satellite Integrated Networks: Joint Local Computation and Data Offloadingcited by 5
  12. 2024Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learningcited by 5
10 more
  1. 2023Decentralised Semi-supervised Onboard Learning for Scene Classification in Low-Earth Orbitcited by 4
  2. 2024Machine Learning in Space: Surveying the Robustness of on-board ML models to Radiationcited by 3
  3. 2024Scheduling for On-Board Federated Learning with Satellite Clusterscited by 2
  4. 2024Space for Improvement: Navigating the Design Space for Federated Learning in Satellite Constellationscited by 1
  5. 2025Brain-Inspired Decentralized Satellite Learning in Space Computing Power Networkscited by 1
  6. 2022Detection and Prevention Against Poisoning Attacks in Federated Learningcited by 0
  7. 2024Sparse Incremental Aggregation in Multi-Hop Federated Learningcited by 0
  8. 2024Heterogeneity: An Open Challenge for Federated On-board Machine Learningcited by 0
  9. 2026Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddingscited by 0
  10. 2026When Is Availability-Aware Training Worth It? A Benchmark and Empirical Study of Interruption-Resilient Optimization Under Predictable Compute Schedulescited by 0