# FedGSM: Efficient Federated Learning for LEO Constellations with Gradient Staleness Mitigation

arXiv: https://arxiv.org/abs/2304.08537 · HTML: https://mlsanity.com/paper/2304.08537/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2023.

## Built on by (most cited first, 8 of 8)

- [FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networks](https://mlsanity.com/paper/2311.01483/) (2023)
- [Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDM](https://mlsanity.com/paper/2401.00685/) (2024)
- [Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learning](https://mlsanity.com/paper/2401.15541/) (2024)
- [Towards Satellite Non-IID Imagery: A Spectral Clustering-Assisted Federated Learning Approach](https://mlsanity.com/paper/2410.13602/) (2024)
- [Decentralized Trust for Space AI: Blockchain-Based Federated Learning Across Multi-Vendor LEO Satellite Networks](https://mlsanity.com/paper/2512.08882/) (2025)
- [Heterogeneity: An Open Challenge for Federated On-board Machine Learning](https://mlsanity.com/paper/2408.06903/) (2024)
- [Satellite Federated Fine-Tuning for Foundation Models in Space Computing Power Networks](https://mlsanity.com/paper/2504.10403/) (2025)
- [FedRings: A Scalable and Topology-Aware Federated Learning Framework for LEO Satellite Constellations](https://mlsanity.com/paper/2608.03436/) (2026)

## Abstract (arXiv)

Recent advancements in space technology have equipped low Earth Orbit (LEO) satellites with the capability to perform complex functions and run AI applications. Federated Learning (FL) on LEO satellites enables collaborative training of a global ML model without the need for sharing large datasets. However, intermittent connectivity between satellites and ground stations can lead to stale gradients and unstable learning, thereby limiting learning performance. In this paper, we propose FedGSM, a novel asynchronous FL algorithm that introduces a compensation mechanism to mitigate gradient staleness. FedGSM leverages the deterministic and time-varying topology of the orbits to offset the negative effects of staleness. Our simulation results demonstrate that FedGSM outperforms state-of-the-art algorithms for both IID and non-IID datasets, underscoring its effectiveness and advantages. We also investigate the effect of system parameters.