Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286375442> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4286375442 endingPage "18" @default.
- W4286375442 startingPage "2" @default.
- W4286375442 abstract "Federated learning (FL) is a powerful distributed machine learning framework where a server aggregates models trained by different clients without accessing their private data. Hierarchical FL, with a client-edge-cloud aggregation hierarchy, can effectively leverage both the cloud server's access to many clients' data and the edge servers' closeness to the clients to achieve a high communication efficiency. Neural network quantization can further reduce the communication overhead during model uploading. To fully exploit the advantages of hierarchical FL, an accurate convergence analysis with respect to the key system parameters is needed. Unfortunately, existing analysis is loose and does not consider model quantization. In this paper, we derive a tighter convergence bound for hierarchical FL with quantization. The convergence result leads to practical guidelines for important design problems such as the client-edge aggregation and edge-client association strategies. Based on the obtained analytical results, we optimize the two aggregation intervals and show that the client-edge aggregation interval should slowly decay while the edge-cloud aggregation interval needs to adapt to the ratio of the client-edge and edge-cloud propagation delay. Simulation results shall verify the design guidelines and demonstrate the effectiveness of the proposed aggregation strategy." @default.
- W4286375442 created "2022-07-21" @default.
- W4286375442 creator A5009944050 @default.
- W4286375442 creator A5025467937 @default.
- W4286375442 creator A5060020916 @default.
- W4286375442 creator A5079052203 @default.
- W4286375442 date "2023-01-01" @default.
- W4286375442 modified "2023-10-06" @default.
- W4286375442 title "Hierarchical Federated Learning With Quantization: Convergence Analysis and System Design" @default.
- W4286375442 cites W2344423009 @default.
- W4286375442 cites W2624989916 @default.
- W4286375442 cites W2920095265 @default.
- W4286375442 cites W2963318081 @default.
- W4286375442 cites W2963433607 @default.
- W4286375442 cites W2979495156 @default.
- W4286375442 cites W2982650630 @default.
- W4286375442 cites W3004277316 @default.
- W4286375442 cites W3037582816 @default.
- W4286375442 cites W3041971333 @default.
- W4286375442 cites W3045638580 @default.
- W4286375442 cites W3046056026 @default.
- W4286375442 cites W3164900515 @default.
- W4286375442 cites W3214755690 @default.
- W4286375442 doi "https://doi.org/10.1109/twc.2022.3190512" @default.
- W4286375442 hasPublicationYear "2023" @default.
- W4286375442 type Work @default.
- W4286375442 citedByCount "4" @default.
- W4286375442 countsByYear W42863754422023 @default.
- W4286375442 crossrefType "journal-article" @default.
- W4286375442 hasAuthorship W4286375442A5009944050 @default.
- W4286375442 hasAuthorship W4286375442A5025467937 @default.
- W4286375442 hasAuthorship W4286375442A5060020916 @default.
- W4286375442 hasAuthorship W4286375442A5079052203 @default.
- W4286375442 hasBestOaLocation W42863754422 @default.
- W4286375442 hasConcept C111919701 @default.
- W4286375442 hasConcept C11413529 @default.
- W4286375442 hasConcept C119857082 @default.
- W4286375442 hasConcept C120314980 @default.
- W4286375442 hasConcept C138236772 @default.
- W4286375442 hasConcept C153083717 @default.
- W4286375442 hasConcept C154945302 @default.
- W4286375442 hasConcept C162307627 @default.
- W4286375442 hasConcept C165696696 @default.
- W4286375442 hasConcept C28855332 @default.
- W4286375442 hasConcept C31258907 @default.
- W4286375442 hasConcept C38652104 @default.
- W4286375442 hasConcept C41008148 @default.
- W4286375442 hasConcept C71901391 @default.
- W4286375442 hasConcept C79974875 @default.
- W4286375442 hasConcept C80444323 @default.
- W4286375442 hasConcept C93996380 @default.
- W4286375442 hasConceptScore W4286375442C111919701 @default.
- W4286375442 hasConceptScore W4286375442C11413529 @default.
- W4286375442 hasConceptScore W4286375442C119857082 @default.
- W4286375442 hasConceptScore W4286375442C120314980 @default.
- W4286375442 hasConceptScore W4286375442C138236772 @default.
- W4286375442 hasConceptScore W4286375442C153083717 @default.
- W4286375442 hasConceptScore W4286375442C154945302 @default.
- W4286375442 hasConceptScore W4286375442C162307627 @default.
- W4286375442 hasConceptScore W4286375442C165696696 @default.
- W4286375442 hasConceptScore W4286375442C28855332 @default.
- W4286375442 hasConceptScore W4286375442C31258907 @default.
- W4286375442 hasConceptScore W4286375442C38652104 @default.
- W4286375442 hasConceptScore W4286375442C41008148 @default.
- W4286375442 hasConceptScore W4286375442C71901391 @default.
- W4286375442 hasConceptScore W4286375442C79974875 @default.
- W4286375442 hasConceptScore W4286375442C80444323 @default.
- W4286375442 hasConceptScore W4286375442C93996380 @default.
- W4286375442 hasIssue "1" @default.
- W4286375442 hasLocation W42863754421 @default.
- W4286375442 hasLocation W42863754422 @default.
- W4286375442 hasLocation W42863754423 @default.
- W4286375442 hasOpenAccess W4286375442 @default.
- W4286375442 hasPrimaryLocation W42863754421 @default.
- W4286375442 hasRelatedWork W143242780 @default.
- W4286375442 hasRelatedWork W2052094875 @default.
- W4286375442 hasRelatedWork W2580692153 @default.
- W4286375442 hasRelatedWork W2743003114 @default.
- W4286375442 hasRelatedWork W2945616868 @default.
- W4286375442 hasRelatedWork W2969040573 @default.
- W4286375442 hasRelatedWork W3006227554 @default.
- W4286375442 hasRelatedWork W3106610906 @default.
- W4286375442 hasRelatedWork W3117321386 @default.
- W4286375442 hasRelatedWork W4313145167 @default.
- W4286375442 hasVolume "22" @default.
- W4286375442 isParatext "false" @default.
- W4286375442 isRetracted "false" @default.
- W4286375442 workType "article" @default.