Abstract
In Low Earth Orbit (LEO) mega constellations, there are relevant use cases, such as inference based on satellite imaging, in which a large number of satellites collaboratively train a machine learning model without sharing their local datasets. To address this problem, we propose a new set of algorithms based on Federated learning (FL), including a novel asynchronous FL procedure based on FedAvg that exhibits better robustness against heterogeneous scenarios than the state-of-the-art. Extensive numerical evaluations based on MNIST and CIFAR-10 datasets highlight the fast convergence speed and excellent asymptotic test accuracy of the proposed method.
Highlights
Constellations of small satellites flying in Low Earth Orbit (LEO) are a cost-efficient and versatile alternative to traditional big satellites in medium Earth and geostationary orbits
The distributed machine learning (ML) paradigm taking data heterogeneity and limited connectivity into account is known as federated learning (FL) [11], [12]
We numerically evaluate the performance of the proposed algorithms in terms of the test accuracy on the MNIST [18] and CIFAR-10 [19] datasets
Summary
Constellations of small satellites flying in Low Earth Orbit (LEO) are a cost-efficient and versatile alternative to traditional big satellites in medium Earth and geostationary orbits. Our key contributions are that we: 1) define the LEO FL scenario and identify core challenges compared to conventional FL; 2) propose an algorithmic framework and communication protocol for satellite FL; 3) adapt FedAvg [12] and FedAsync [14] to this scenario and propose a novel asynchronous variant of FedAvg that is well suited for ground-assisted FL in satellite constellations, and 4) numerically evaluate the discussed algorithms to verify our theoretical considerations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.