Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367163048> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4367163048 endingPage "1" @default.
- W4367163048 startingPage "1" @default.
- W4367163048 abstract "Motivated by the increasing computational capabilities of wireless devices, as well as unprecedented levels of user- and device-generated data, new distributed machine learning (ML) methods have emerged. In the wireless community, Federated Learning (FL) is of particular interest due to its communication efficiency and its ability to deal with the problem of non-IID data. FL training can be accelerated by a wireless communication method called Over-the-Air Computation (AirComp) which harnesses the interference of simultaneous uplink transmissions to efficiently aggregate model updates. However, since AirComp utilizes analog communication, it introduces inevitable estimation errors. In this paper, we study the impact of such estimation errors on the convergence of FL and propose retransmissions as a method to improve FL accuracy over resource-constrained wireless networks. First, we derive the optimal AirComp power control scheme with retransmissions over static channels. Then, we investigate the performance of Over-the-Air FL with retransmissions and find two upper bounds on the FL loss function. Numerical results demonstrate that the power control scheme offers significant reductions in mean squared error. Additionally, we provide simulation results on MNIST classification with a deep neural network that reveals significant improvements in classification accuracy for low-SNR scenarios." @default.
- W4367163048 created "2023-04-28" @default.
- W4367163048 creator A5075982238 @default.
- W4367163048 creator A5077148700 @default.
- W4367163048 creator A5086707024 @default.
- W4367163048 date "2023-01-01" @default.
- W4367163048 modified "2023-10-14" @default.
- W4367163048 title "Federated Learning Over-the-Air by Retransmissions" @default.
- W4367163048 doi "https://doi.org/10.1109/twc.2023.3268742" @default.
- W4367163048 hasPublicationYear "2023" @default.
- W4367163048 type Work @default.
- W4367163048 citedByCount "1" @default.
- W4367163048 countsByYear W43671630482023 @default.
- W4367163048 crossrefType "journal-article" @default.
- W4367163048 hasAuthorship W4367163048A5075982238 @default.
- W4367163048 hasAuthorship W4367163048A5077148700 @default.
- W4367163048 hasAuthorship W4367163048A5086707024 @default.
- W4367163048 hasBestOaLocation W43671630481 @default.
- W4367163048 hasConcept C108037233 @default.
- W4367163048 hasConcept C119857082 @default.
- W4367163048 hasConcept C121332964 @default.
- W4367163048 hasConcept C138660444 @default.
- W4367163048 hasConcept C162324750 @default.
- W4367163048 hasConcept C163258240 @default.
- W4367163048 hasConcept C190502265 @default.
- W4367163048 hasConcept C2777303404 @default.
- W4367163048 hasConcept C31258907 @default.
- W4367163048 hasConcept C41008148 @default.
- W4367163048 hasConcept C50522688 @default.
- W4367163048 hasConcept C50644808 @default.
- W4367163048 hasConcept C555944384 @default.
- W4367163048 hasConcept C56685638 @default.
- W4367163048 hasConcept C62520636 @default.
- W4367163048 hasConcept C76155785 @default.
- W4367163048 hasConcept C79403827 @default.
- W4367163048 hasConceptScore W4367163048C108037233 @default.
- W4367163048 hasConceptScore W4367163048C119857082 @default.
- W4367163048 hasConceptScore W4367163048C121332964 @default.
- W4367163048 hasConceptScore W4367163048C138660444 @default.
- W4367163048 hasConceptScore W4367163048C162324750 @default.
- W4367163048 hasConceptScore W4367163048C163258240 @default.
- W4367163048 hasConceptScore W4367163048C190502265 @default.
- W4367163048 hasConceptScore W4367163048C2777303404 @default.
- W4367163048 hasConceptScore W4367163048C31258907 @default.
- W4367163048 hasConceptScore W4367163048C41008148 @default.
- W4367163048 hasConceptScore W4367163048C50522688 @default.
- W4367163048 hasConceptScore W4367163048C50644808 @default.
- W4367163048 hasConceptScore W4367163048C555944384 @default.
- W4367163048 hasConceptScore W4367163048C56685638 @default.
- W4367163048 hasConceptScore W4367163048C62520636 @default.
- W4367163048 hasConceptScore W4367163048C76155785 @default.
- W4367163048 hasConceptScore W4367163048C79403827 @default.
- W4367163048 hasLocation W43671630481 @default.
- W4367163048 hasLocation W43671630482 @default.
- W4367163048 hasLocation W43671630483 @default.
- W4367163048 hasOpenAccess W4367163048 @default.
- W4367163048 hasPrimaryLocation W43671630481 @default.
- W4367163048 hasRelatedWork W2032062935 @default.
- W4367163048 hasRelatedWork W2056563920 @default.
- W4367163048 hasRelatedWork W2155452634 @default.
- W4367163048 hasRelatedWork W2253628853 @default.
- W4367163048 hasRelatedWork W2376184308 @default.
- W4367163048 hasRelatedWork W2377202261 @default.
- W4367163048 hasRelatedWork W2908596665 @default.
- W4367163048 hasRelatedWork W4310746796 @default.
- W4367163048 hasRelatedWork W4320029478 @default.
- W4367163048 hasRelatedWork W4385483253 @default.
- W4367163048 isParatext "false" @default.
- W4367163048 isRetracted "false" @default.
- W4367163048 workType "article" @default.