Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378718164> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4378718164 abstract "Federated learning (FL) is a popular privacy-preserving distributed training scheme, where multiple devices collaborate to train machine learning models by uploading local model updates. To improve communication efficiency, over-the-air computation (AirComp) has been applied to FL, which leverages analog modulation to harness the superposition property of radio waves such that numerous devices can upload their model updates concurrently for aggregation. However, the uplink channel noise incurs considerable model aggregation distortion, which is critically determined by the device scheduling and compromises the learned model performance. In this paper, we propose a probabilistic device scheduling framework for over-the-air FL, named PO-FL, to mitigate the negative impact of channel noise, where each device is scheduled according to a certain probability and its model update is reweighted using this probability in aggregation. We prove the unbiasedness of this aggregation scheme and demonstrate the convergence of PO-FL on both convex and non-convex loss functions. Our convergence bounds unveil that the device scheduling affects the learning performance through the communication distortion and global update variance. Based on the convergence analysis, we further develop a channel and gradient-importance aware algorithm to optimize the device scheduling probabilities in PO-FL. Extensive simulation results show that the proposed PO-FL framework with channel and gradient-importance awareness achieves faster convergence and produces better models than baseline methods." @default.
- W4378718164 created "2023-05-30" @default.
- W4378718164 creator A5013079905 @default.
- W4378718164 creator A5044718793 @default.
- W4378718164 creator A5051439492 @default.
- W4378718164 creator A5073624141 @default.
- W4378718164 creator A5087982402 @default.
- W4378718164 date "2023-05-26" @default.
- W4378718164 modified "2023-10-16" @default.
- W4378718164 title "Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning" @default.
- W4378718164 doi "https://doi.org/10.48550/arxiv.2305.16854" @default.
- W4378718164 hasPublicationYear "2023" @default.
- W4378718164 type Work @default.
- W4378718164 citedByCount "0" @default.
- W4378718164 crossrefType "posted-content" @default.
- W4378718164 hasAuthorship W4378718164A5013079905 @default.
- W4378718164 hasAuthorship W4378718164A5044718793 @default.
- W4378718164 hasAuthorship W4378718164A5051439492 @default.
- W4378718164 hasAuthorship W4378718164A5073624141 @default.
- W4378718164 hasAuthorship W4378718164A5087982402 @default.
- W4378718164 hasBestOaLocation W43787181641 @default.
- W4378718164 hasConcept C111919701 @default.
- W4378718164 hasConcept C11413529 @default.
- W4378718164 hasConcept C120314980 @default.
- W4378718164 hasConcept C126255220 @default.
- W4378718164 hasConcept C127162648 @default.
- W4378718164 hasConcept C134306372 @default.
- W4378718164 hasConcept C138660444 @default.
- W4378718164 hasConcept C154945302 @default.
- W4378718164 hasConcept C206729178 @default.
- W4378718164 hasConcept C27753989 @default.
- W4378718164 hasConcept C31258907 @default.
- W4378718164 hasConcept C33923547 @default.
- W4378718164 hasConcept C41008148 @default.
- W4378718164 hasConcept C49937458 @default.
- W4378718164 hasConcept C71901391 @default.
- W4378718164 hasConcept C79403827 @default.
- W4378718164 hasConcept C97541855 @default.
- W4378718164 hasConceptScore W4378718164C111919701 @default.
- W4378718164 hasConceptScore W4378718164C11413529 @default.
- W4378718164 hasConceptScore W4378718164C120314980 @default.
- W4378718164 hasConceptScore W4378718164C126255220 @default.
- W4378718164 hasConceptScore W4378718164C127162648 @default.
- W4378718164 hasConceptScore W4378718164C134306372 @default.
- W4378718164 hasConceptScore W4378718164C138660444 @default.
- W4378718164 hasConceptScore W4378718164C154945302 @default.
- W4378718164 hasConceptScore W4378718164C206729178 @default.
- W4378718164 hasConceptScore W4378718164C27753989 @default.
- W4378718164 hasConceptScore W4378718164C31258907 @default.
- W4378718164 hasConceptScore W4378718164C33923547 @default.
- W4378718164 hasConceptScore W4378718164C41008148 @default.
- W4378718164 hasConceptScore W4378718164C49937458 @default.
- W4378718164 hasConceptScore W4378718164C71901391 @default.
- W4378718164 hasConceptScore W4378718164C79403827 @default.
- W4378718164 hasConceptScore W4378718164C97541855 @default.
- W4378718164 hasLocation W43787181641 @default.
- W4378718164 hasOpenAccess W4378718164 @default.
- W4378718164 hasPrimaryLocation W43787181641 @default.
- W4378718164 hasRelatedWork W1882733036 @default.
- W4378718164 hasRelatedWork W1992741870 @default.
- W4378718164 hasRelatedWork W2099266623 @default.
- W4378718164 hasRelatedWork W2109998134 @default.
- W4378718164 hasRelatedWork W2160425906 @default.
- W4378718164 hasRelatedWork W2292891061 @default.
- W4378718164 hasRelatedWork W2358870483 @default.
- W4378718164 hasRelatedWork W2389719923 @default.
- W4378718164 hasRelatedWork W2546696010 @default.
- W4378718164 hasRelatedWork W2997367849 @default.
- W4378718164 isParatext "false" @default.
- W4378718164 isRetracted "false" @default.
- W4378718164 workType "article" @default.