FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094368349> ?p ?o ?g. }

• W3094368349 endingPage "1584" @default.
• W3094368349 startingPage "1569" @default.
• W3094368349 abstract "Federated learning has generated significant interest, with nearly all works focused on a star topology where nodes/devices are each connected to a central server. We migrate away from this architecture and extend it through the network dimension to the case where there are multiple layers of nodes between the end devices and the server. Specifically, we develop multi-stage hybrid federated learning (MH-FL), a hybrid of intra- and inter-layer model learning that considers the network as a multi-layer cluster-based structure. MH-FL considers the topology structures among the nodes in the clusters, including local networks formed via device-to-device (D2D) communications, and presumes a semi-decentralized architecture for federated learning. It orchestrates the devices at different network layers in a collaborative/cooperative manner (i.e., using D2D interactions) to form local consensus on the model parameters and combines it with multi-stage parameter relaying between layers of the tree-shaped hierarchy. We derive the upper bound of convergence for MH-FL with respect to parameters of the network topology (e.g., the spectral radius) and the learning algorithm (e.g., the number of D2D rounds in different clusters). We obtain a set of policies for the D2D rounds at different clusters to guarantee either a finite optimality gap or convergence to the global optimum. We then develop a distributed control algorithm for MH-FL to tune the D2D rounds in each cluster over time to meet specific convergence criteria. Our experiments on real-world datasets verify our analytical results and demonstrate the advantages of MH-FL in terms of resource utilization metrics." @default.
• W3094368349 created "2020-10-29" @default.
• W3094368349 creator A5001355478 @default.
• W3094368349 creator A5017461331 @default.
• W3094368349 creator A5020399355 @default.
• W3094368349 creator A5027155270 @default.
• W3094368349 creator A5059750214 @default.
• W3094368349 creator A5064634430 @default.
• W3094368349 creator A5064822688 @default.
• W3094368349 date "2022-08-01" @default.
• W3094368349 modified "2023-10-05" @default.
• W3094368349 title "Multi-Stage Hybrid Federated Learning Over Large-Scale D2D-Enabled Fog Networks" @default.
• W3094368349 cites W1919998456 @default.
• W3094368349 cites W1969281101 @default.
• W3094368349 cites W1998667180 @default.
• W3094368349 cites W2029443449 @default.
• W3094368349 cites W2044212084 @default.
• W3094368349 cites W2070449754 @default.
• W3094368349 cites W2074796812 @default.
• W3094368349 cites W2090321073 @default.
• W3094368349 cites W2092620240 @default.
• W3094368349 cites W2108777122 @default.
• W3094368349 cites W2117130368 @default.
• W3094368349 cites W2141125852 @default.
• W3094368349 cites W2142184324 @default.
• W3094368349 cites W2145554346 @default.
• W3094368349 cites W2151685478 @default.
• W3094368349 cites W2155356457 @default.
• W3094368349 cites W2155723880 @default.
• W3094368349 cites W2606084320 @default.
• W3094368349 cites W2762590152 @default.
• W3094368349 cites W2900917720 @default.
• W3094368349 cites W2903836693 @default.
• W3094368349 cites W2920095265 @default.
• W3094368349 cites W2962766718 @default.
• W3094368349 cites W2963136846 @default.
• W3094368349 cites W2963318081 @default.
• W3094368349 cites W2985108934 @default.
• W3094368349 cites W2996845627 @default.
• W3094368349 cites W3001299093 @default.
• W3094368349 cites W3004277316 @default.
• W3094368349 cites W3006919779 @default.
• W3094368349 cites W3015613093 @default.
• W3094368349 cites W3015901293 @default.
• W3094368349 cites W3021096439 @default.
• W3094368349 cites W3037582816 @default.
• W3094368349 cites W3045638580 @default.
• W3094368349 cites W3045898871 @default.
• W3094368349 cites W3047595056 @default.
• W3094368349 cites W3103657382 @default.
• W3094368349 cites W3121122428 @default.
• W3094368349 cites W3155160971 @default.
• W3094368349 cites W3192113790 @default.
• W3094368349 doi "https://doi.org/10.1109/tnet.2022.3143495" @default.
• W3094368349 hasPublicationYear "2022" @default.
• W3094368349 type Work @default.
• W3094368349 sameAs 3094368349 @default.
• W3094368349 citedByCount "22" @default.
• W3094368349 countsByYear W30943683492020 @default.
• W3094368349 countsByYear W30943683492021 @default.
• W3094368349 countsByYear W30943683492022 @default.
• W3094368349 countsByYear W30943683492023 @default.
• W3094368349 crossrefType "journal-article" @default.
• W3094368349 hasAuthorship W3094368349A5001355478 @default.
• W3094368349 hasAuthorship W3094368349A5017461331 @default.
• W3094368349 hasAuthorship W3094368349A5020399355 @default.
• W3094368349 hasAuthorship W3094368349A5027155270 @default.
• W3094368349 hasAuthorship W3094368349A5059750214 @default.
• W3094368349 hasAuthorship W3094368349A5064634430 @default.
• W3094368349 hasAuthorship W3094368349A5064822688 @default.
• W3094368349 hasBestOaLocation W30943683492 @default.
• W3094368349 hasConcept C114614502 @default.
• W3094368349 hasConcept C120314980 @default.
• W3094368349 hasConcept C162324750 @default.
• W3094368349 hasConcept C164866538 @default.
• W3094368349 hasConcept C184720557 @default.
• W3094368349 hasConcept C199845137 @default.
• W3094368349 hasConcept C202444582 @default.
• W3094368349 hasConcept C2777303404 @default.
• W3094368349 hasConcept C31258907 @default.
• W3094368349 hasConcept C33676613 @default.
• W3094368349 hasConcept C33923547 @default.
• W3094368349 hasConcept C41008148 @default.
• W3094368349 hasConcept C50522688 @default.
• W3094368349 hasConcept C93996380 @default.
• W3094368349 hasConceptScore W3094368349C114614502 @default.
• W3094368349 hasConceptScore W3094368349C120314980 @default.
• W3094368349 hasConceptScore W3094368349C162324750 @default.
• W3094368349 hasConceptScore W3094368349C164866538 @default.
• W3094368349 hasConceptScore W3094368349C184720557 @default.
• W3094368349 hasConceptScore W3094368349C199845137 @default.
• W3094368349 hasConceptScore W3094368349C202444582 @default.
• W3094368349 hasConceptScore W3094368349C2777303404 @default.
• W3094368349 hasConceptScore W3094368349C31258907 @default.
• W3094368349 hasConceptScore W3094368349C33676613 @default.
• W3094368349 hasConceptScore W3094368349C33923547 @default.
• W3094368349 hasConceptScore W3094368349C41008148 @default.
• W3094368349 hasConceptScore W3094368349C50522688 @default.

• next