Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387415116> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4387415116 endingPage "6" @default.
- W4387415116 startingPage "1" @default.
- W4387415116 abstract "Decentralized Federated Learning (DFL) is a federated learning framework without any central controllers. With the development of Low Earth Orbit (LEO) satellite constellations, LEO satellites can be used to train a machine learning model collaboratively through DFL. However, due to the energy limitations of the satellites, DFL with satellites has higher requirements on the latency. In this paper, we investigate how to minimize the convergence time of DFL with satellites by designing the number of satellites in each orbit and the number of orbits. In addition to considering the total energy cost and the distance constraints in satellite communication, we also consider guaranteeing the DFL performance in the problem of minimizing the convergence time. However, obtaining closed-form solutions to this problem is difficult since the target is non-convex and the performance is hard to evaluate directly. To address these issues, we derive an upper bound on the convergence time and transform it into a quasi-convex function first. Then, we derive the convergence bound of DFL with respect to the number of satellites and orbits. Based on these two bounds, we reformulate the problem and obtain the closed-form expressions of the optimal number of satellites and orbits. Simulation results confirm the impact of these numbers on the convergence time and verify the effectiveness of the proposed scheme." @default.
- W4387415116 created "2023-10-07" @default.
- W4387415116 creator A5033733873 @default.
- W4387415116 creator A5054116115 @default.
- W4387415116 date "2023-01-01" @default.
- W4387415116 modified "2023-10-08" @default.
- W4387415116 title "Convergence Time Optimization for Decentralized Federated Learning with LEO Satellites via Number Control" @default.
- W4387415116 doi "https://doi.org/10.1109/tvt.2023.3322461" @default.
- W4387415116 hasPublicationYear "2023" @default.
- W4387415116 type Work @default.
- W4387415116 citedByCount "0" @default.
- W4387415116 crossrefType "journal-article" @default.
- W4387415116 hasAuthorship W4387415116A5033733873 @default.
- W4387415116 hasAuthorship W4387415116A5054116115 @default.
- W4387415116 hasConcept C112680207 @default.
- W4387415116 hasConcept C11413529 @default.
- W4387415116 hasConcept C121332964 @default.
- W4387415116 hasConcept C126255220 @default.
- W4387415116 hasConcept C127413603 @default.
- W4387415116 hasConcept C1276947 @default.
- W4387415116 hasConcept C134306372 @default.
- W4387415116 hasConcept C137836250 @default.
- W4387415116 hasConcept C14036430 @default.
- W4387415116 hasConcept C145446738 @default.
- W4387415116 hasConcept C146978453 @default.
- W4387415116 hasConcept C157972887 @default.
- W4387415116 hasConcept C162324750 @default.
- W4387415116 hasConcept C19269812 @default.
- W4387415116 hasConcept C196644772 @default.
- W4387415116 hasConcept C2524010 @default.
- W4387415116 hasConcept C2777303404 @default.
- W4387415116 hasConcept C33923547 @default.
- W4387415116 hasConcept C41008148 @default.
- W4387415116 hasConcept C50522688 @default.
- W4387415116 hasConcept C70352696 @default.
- W4387415116 hasConcept C76155785 @default.
- W4387415116 hasConcept C77553402 @default.
- W4387415116 hasConcept C78458016 @default.
- W4387415116 hasConcept C82876162 @default.
- W4387415116 hasConcept C86803240 @default.
- W4387415116 hasConceptScore W4387415116C112680207 @default.
- W4387415116 hasConceptScore W4387415116C11413529 @default.
- W4387415116 hasConceptScore W4387415116C121332964 @default.
- W4387415116 hasConceptScore W4387415116C126255220 @default.
- W4387415116 hasConceptScore W4387415116C127413603 @default.
- W4387415116 hasConceptScore W4387415116C1276947 @default.
- W4387415116 hasConceptScore W4387415116C134306372 @default.
- W4387415116 hasConceptScore W4387415116C137836250 @default.
- W4387415116 hasConceptScore W4387415116C14036430 @default.
- W4387415116 hasConceptScore W4387415116C145446738 @default.
- W4387415116 hasConceptScore W4387415116C146978453 @default.
- W4387415116 hasConceptScore W4387415116C157972887 @default.
- W4387415116 hasConceptScore W4387415116C162324750 @default.
- W4387415116 hasConceptScore W4387415116C19269812 @default.
- W4387415116 hasConceptScore W4387415116C196644772 @default.
- W4387415116 hasConceptScore W4387415116C2524010 @default.
- W4387415116 hasConceptScore W4387415116C2777303404 @default.
- W4387415116 hasConceptScore W4387415116C33923547 @default.
- W4387415116 hasConceptScore W4387415116C41008148 @default.
- W4387415116 hasConceptScore W4387415116C50522688 @default.
- W4387415116 hasConceptScore W4387415116C70352696 @default.
- W4387415116 hasConceptScore W4387415116C76155785 @default.
- W4387415116 hasConceptScore W4387415116C77553402 @default.
- W4387415116 hasConceptScore W4387415116C78458016 @default.
- W4387415116 hasConceptScore W4387415116C82876162 @default.
- W4387415116 hasConceptScore W4387415116C86803240 @default.
- W4387415116 hasLocation W43874151161 @default.
- W4387415116 hasOpenAccess W4387415116 @default.
- W4387415116 hasPrimaryLocation W43874151161 @default.
- W4387415116 hasRelatedWork W1504636466 @default.
- W4387415116 hasRelatedWork W1568632544 @default.
- W4387415116 hasRelatedWork W2187449906 @default.
- W4387415116 hasRelatedWork W2382519356 @default.
- W4387415116 hasRelatedWork W2502457263 @default.
- W4387415116 hasRelatedWork W2801080295 @default.
- W4387415116 hasRelatedWork W2901245944 @default.
- W4387415116 hasRelatedWork W3011190762 @default.
- W4387415116 hasRelatedWork W4322709807 @default.
- W4387415116 hasRelatedWork W4377967113 @default.
- W4387415116 isParatext "false" @default.
- W4387415116 isRetracted "false" @default.
- W4387415116 workType "article" @default.