Federated Learning with Dynamic Aggregation Based on Connection Density at Satellites and Ground Stations

Jiang, Lin; Li, Yusen; Xu, Zhuo

doi:10.1109/satellite55519.2022.00014

Cited by 9 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the primary reason for the feasibility of synchronous terrestrial orchestration is the usage of multiple geographically distributed GSs that act as a distributed PS. While the authors observe correctly that latency between GSs is small compared to GSLs, mechanisms to either ensure consistency between GSs or a hierarchical FL approach would be required in a practical system implementation of [22].…”

Section: A Related Workmentioning

confidence: 81%

“…Staleness in asynchronous SFL is further investigated in [21], which introduces an asynchronous update rule based on the notion that staleness effects in SFL are similar in consecutive training epochs. In [22] the connection bottleneck is tackled by combining synchronous orchestration with a dynamic aggregation rule that ignores stragglers. However, the primary reason for the feasibility of synchronous terrestrial orchestration is the usage of multiple geographically distributed GSs that act as a distributed PS.…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

On-Board Federated Learning for Dense LEO Constellations

Razmi

Matthiesen

Dekorsy

et al. 2022

ICC 2022 - IEEE International Conference on Communications

View full text Add to dashboard Cite

The emergence of mega-constellations of interconnected satellites has a major impact on the integration of cellular wireless and non-terrestrial networks (NTN). This paper studies the problem of running a federated learning (FL) algorithm within a low Earth orbit (LEO) constellation of satellites connected with intra-orbit inter-satellite links (ISL). Satellites apply on-board machine learning and transmit the local parameters to the parameter server (PS). The main contribution is a novel approach to enhance FL in satellite constellations using intra-orbit ISLs. The key idea is to rely on the predictability of satellite visits to create a system design in which ISLs mitigate the impact of intermittent connectivity and transmit the aggregated parameters to the PS. We first devise a synchronous FL, which is then extended towards an asynchronous FL for the case of sparse satellite visits to the PS. An efficient use of the satellite resources is attained by sparsification-based compression the aggregated parameters of each orbit before forwarding to the PS. Performance is evaluated in terms of accuracy and the required size of data to be transmitted. The numerical results indicate a faster convergence rate of the presented approach compared with the state-of-the-art FL on satellite constellations.

show abstract

Section: A Related Workmentioning

confidence: 81%

Section: A Related Workmentioning

confidence: 99%