Abstract | ||
---|---|---|
Distributed training of machine learning models directly on satellites in low Earth orbit (LEO) is considered. Based on a federated learning (FL) algorithm specifically targeted at the unique challenges of the satellite scenario, we design a scheduler that exploits the predictability of visiting times between ground stations (GS) and satellites to reduce model staleness. Numerical experiments show that this can improve the convergence speed by a factor three. |
Year | Venue | DocType |
---|---|---|
2022 | European Signal Processing Conference (EUSIPCO) | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nasrin Razmi | 1 | 0 | 0.68 |
Bho Matthiesen | 2 | 0 | 1.01 |
Armin Dekorsy | 3 | 0 | 2.37 |
Popovski Petar | 4 | 4262 | 316.91 |