# On-Board Federated Learning for Dense LEO Constellations

arXiv: https://arxiv.org/abs/2111.12769 · HTML: https://mlsanity.com/paper/2111.12769/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2021.

## Built on by (most cited first, 22 of 22)

- [FedHAP: Fast Federated Learning for LEO Constellations Using Collaborative HAPs](https://mlsanity.com/paper/2205.07216/) (2022)
- [Federated Learning in Satellite Constellations](https://mlsanity.com/paper/2206.00307/) (2022)
- [AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platforms](https://mlsanity.com/paper/2212.11522/) (2022)
- [Optimizing Federated Learning in LEO Satellite Constellations via Intra-Plane Model Propagation and Sink Satellite Scheduling](https://mlsanity.com/paper/2302.13447/) (2023)
- [Satellite Federated Edge Learning: Architecture Design and Convergence Analysis](https://mlsanity.com/paper/2404.01875/) (2024)
- [One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes](https://mlsanity.com/paper/2305.12316/) (2023)
- [Edge Selection and Clustering for Federated Learning in Optical Inter-LEO Satellite Constellation](https://mlsanity.com/paper/2303.16071/) (2023)
- [Secure and Efficient Federated Learning in LEO Constellations using Decentralized Key Generation and On-Orbit Model Aggregation](https://mlsanity.com/paper/2309.01828/) (2023)
- [Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDM](https://mlsanity.com/paper/2401.00685/) (2024)
- [Selected Trends in Artificial Intelligence for Space Applications](https://mlsanity.com/paper/2212.06662/) (2022)
- [Cooperative Federated Learning over Ground-to-Satellite Integrated Networks: Joint Local Computation and Data Offloading](https://mlsanity.com/paper/2312.15361/) (2023)
- [Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learning](https://mlsanity.com/paper/2401.15541/) (2024)
- [Decentralised Semi-supervised Onboard Learning for Scene Classification in Low-Earth Orbit](https://mlsanity.com/paper/2305.04059/) (2023)
- [Machine Learning in Space: Surveying the Robustness of on-board ML models to Radiation](https://mlsanity.com/paper/2405.02642/) (2024)
- [Scheduling for On-Board Federated Learning with Satellite Clusters](https://mlsanity.com/paper/2402.09105/) (2024)
- [Space for Improvement: Navigating the Design Space for Federated Learning in Satellite Constellations](https://mlsanity.com/paper/2411.00263/) (2024)
- [Brain-Inspired Decentralized Satellite Learning in Space Computing Power Networks](https://mlsanity.com/paper/2501.15995/) (2025)
- [Detection and Prevention Against Poisoning Attacks in Federated Learning](https://mlsanity.com/paper/2210.14944/) (2022)
- [Sparse Incremental Aggregation in Multi-Hop Federated Learning](https://mlsanity.com/paper/2407.18200/) (2024)
- [Heterogeneity: An Open Challenge for Federated On-board Machine Learning](https://mlsanity.com/paper/2408.06903/) (2024)
- [Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings](https://mlsanity.com/paper/2603.02233/) (2026)
- [When Is Availability-Aware Training Worth It? A Benchmark and Empirical Study of Interruption-Resilient Optimization Under Predictable Compute Schedules](https://mlsanity.com/paper/2609.22087/) (2026)

## 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.