mlsanityData to 14 Oct 2026

One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes

arXiv 2305.12316 ↗First posted 21 May 2023cs.LG cs.NIcited by 7

Not on the map. Why?

Abstract (arXiv)

A Low Earth orbit (LEO) satellite constellation consists of a large number of small satellites traveling in space with high mobility and collecting vast amounts of mobility data such as cloud movement for weather forecast, large herds of animals migrating across geo-regions, spreading of forest fires, and aircraft tracking. Machine learning can be utilized to analyze these mobility data to address global challenges, and Federated Learning (FL) is a promising approach because it eliminates the need for transmitting raw data and hence is both bandwidth and privacy-friendly. However, FL requires many communication rounds between clients (satellites) and the parameter server (PS), leading to substantial delays of up to several days in LEO constellations. In this paper, we propose a novel one-shot FL approach for LEO satellites, called LEOShot, that needs only a single communication round to complete the entire learning process. LEOShot comprises three processes: (i) synthetic data generation, (ii) knowledge distillation, and (iii) virtual model retraining. We evaluate and benchmark LEOShot against the state of the art and the results show that it drastically expedites FL convergence by more than an order of magnitude. Also surprisingly, despite the one-shot nature, its model accuracy is on par with or even outperforms regular iterative FL schemes by a large margin

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 21 May 2023.

Builds on

22 of 30 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2016Wide Residual Networkscited by 3,070
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2020Knowledge Distillation: A Surveycited by 1,603
  6. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  7. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  8. 2018Dataset Distillationcited by 230
  9. 2019One-Shot Federated Learningcited by 125
  10. 2020Distilled One-Shot Federated Learningcited by 109
  11. 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 77
  12. 2018Knowledge Distillation with Adversarial Samples Supporting Decision Boundarycited by 49
10 more
  1. 2021Ground-Assisted Federated Learning in LEO Satellite Constellationscited by 31
  2. 2022FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stationscited by 28
  3. 2021Satellite Based Computing Networks with Federated Learningcited by 25
  4. 2019One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Themcited by 23
  5. 2021On-Board Federated Learning for Dense LEO Constellationscited by 22
  6. 2022FedHAP: Fast Federated Learning for LEO Constellations Using Collaborative HAPscited by 21
  7. 2022AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platformscited by 18
  8. 2020Inter-Plane Inter-Satellite Connectivity in Dense LEO Constellationscited by 12
  9. 2023Optimizing Federated Learning in LEO Satellite Constellations via Intra-Plane Model Propagation and Sink Satellite Schedulingcited by 10
  10. 2022Scheduling for Ground-Assisted Federated Learning in LEO Satellite Constellationscited by 9

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 2.

7 papers.

  1. 2024Federated Distillation: A Surveycited by 15
  2. 2023Secure and Efficient Federated Learning in LEO Constellations using Decentralized Key Generation and On-Orbit Model Aggregationcited by 6
  3. 2024Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDMcited by 6
  4. 2024Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learningcited by 5
  5. 2025Towards One-shot Federated Learning: Advances, Challenges, and Future Directionscited by 2
  6. 2024CAV-AD: A Robust Framework for Detection of Anomalous Data and Malicious Sensors in CAV Networkscited by 1
  7. 2025Decentralized Trust for Space AI: Blockchain-Based Federated Learning Across Multi-Vendor LEO Satellite Networkscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations
  2. 2025A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks
  3. 2026On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellations
  4. 2025OptiVote: Non-Coherent FSO Over-the-Air Majority Vote for Communication-Efficient Distributed Federated Learning in Space Data Centers
  5. 2024Towards Satellite Non-IID Imagery: A Spectral Clustering-Assisted Federated Learning Approach
  6. 2026FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study
  7. 2026MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites
  8. 2026iSatCR: Graph-Empowered Joint Onboard Computing and Routing for LEO Data Delivery