Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308482364> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4308482364 abstract "Does Federated Learning (FL) work when both uplink and downlink communications have errors? How much communication noise can FL handle and what is its impact to the learning performance? This work is devoted to answering these practically important questions by explicitly incorporating both uplink and downlink noisy channels in the FL pipeline. We present several novel convergence analyses of FL over simultaneous uplink and downlink noisy communication channels, which encompass full and partial clients participation, direct model and model differential transmissions, and non-independent and identically distributed (IID) local datasets. These analyses characterize the sufficient conditions for FL over noisy channels to have the same convergence behavior as the ideal case of no communication error. More specifically, in order to maintain the O(1/T) convergence rate of FedAvg with perfect communications, the uplink and downlink signal-to-noise ratio (SNR) for direct model transmissions should be controlled such that they scale as O(t^2) where t is the index of communication rounds, but can stay constant for model differential transmissions. The key insight of these theoretical results is a flying under the radar principle - stochastic gradient descent (SGD) is an inherent noisy process and uplink/downlink communication noises can be tolerated as long as they do not dominate the time-varying SGD noise. We exemplify these theoretical findings with two widely adopted communication techniques - transmit power control and diversity combining - and further validating their performance advantages over the standard methods via extensive numerical experiments using several real-world FL tasks." @default.
- W4308482364 created "2022-11-12" @default.
- W4308482364 creator A5016749653 @default.
- W4308482364 creator A5026281648 @default.
- W4308482364 date "2021-01-06" @default.
- W4308482364 modified "2023-09-26" @default.
- W4308482364 title "Federated Learning over Noisy Channels: Convergence Analysis and Design Examples" @default.
- W4308482364 doi "https://doi.org/10.48550/arxiv.2101.02198" @default.
- W4308482364 hasPublicationYear "2021" @default.
- W4308482364 type Work @default.
- W4308482364 citedByCount "0" @default.
- W4308482364 crossrefType "posted-content" @default.
- W4308482364 hasAuthorship W4308482364A5016749653 @default.
- W4308482364 hasAuthorship W4308482364A5026281648 @default.
- W4308482364 hasBestOaLocation W43084823641 @default.
- W4308482364 hasConcept C105795698 @default.
- W4308482364 hasConcept C115961682 @default.
- W4308482364 hasConcept C122123141 @default.
- W4308482364 hasConcept C127413603 @default.
- W4308482364 hasConcept C138660444 @default.
- W4308482364 hasConcept C13944312 @default.
- W4308482364 hasConcept C141513077 @default.
- W4308482364 hasConcept C154945302 @default.
- W4308482364 hasConcept C162324750 @default.
- W4308482364 hasConcept C24326235 @default.
- W4308482364 hasConcept C2777303404 @default.
- W4308482364 hasConcept C31258907 @default.
- W4308482364 hasConcept C33923547 @default.
- W4308482364 hasConcept C41008148 @default.
- W4308482364 hasConcept C50522688 @default.
- W4308482364 hasConcept C76155785 @default.
- W4308482364 hasConcept C99498987 @default.
- W4308482364 hasConceptScore W4308482364C105795698 @default.
- W4308482364 hasConceptScore W4308482364C115961682 @default.
- W4308482364 hasConceptScore W4308482364C122123141 @default.
- W4308482364 hasConceptScore W4308482364C127413603 @default.
- W4308482364 hasConceptScore W4308482364C138660444 @default.
- W4308482364 hasConceptScore W4308482364C13944312 @default.
- W4308482364 hasConceptScore W4308482364C141513077 @default.
- W4308482364 hasConceptScore W4308482364C154945302 @default.
- W4308482364 hasConceptScore W4308482364C162324750 @default.
- W4308482364 hasConceptScore W4308482364C24326235 @default.
- W4308482364 hasConceptScore W4308482364C2777303404 @default.
- W4308482364 hasConceptScore W4308482364C31258907 @default.
- W4308482364 hasConceptScore W4308482364C33923547 @default.
- W4308482364 hasConceptScore W4308482364C41008148 @default.
- W4308482364 hasConceptScore W4308482364C50522688 @default.
- W4308482364 hasConceptScore W4308482364C76155785 @default.
- W4308482364 hasConceptScore W4308482364C99498987 @default.
- W4308482364 hasLocation W43084823641 @default.
- W4308482364 hasOpenAccess W4308482364 @default.
- W4308482364 hasPrimaryLocation W43084823641 @default.
- W4308482364 hasRelatedWork W2135811491 @default.
- W4308482364 hasRelatedWork W2373697688 @default.
- W4308482364 hasRelatedWork W2771271201 @default.
- W4308482364 hasRelatedWork W2783563119 @default.
- W4308482364 hasRelatedWork W2800059570 @default.
- W4308482364 hasRelatedWork W2808441222 @default.
- W4308482364 hasRelatedWork W2916113261 @default.
- W4308482364 hasRelatedWork W3158928200 @default.
- W4308482364 hasRelatedWork W4290996490 @default.
- W4308482364 hasRelatedWork W4313892825 @default.
- W4308482364 isParatext "false" @default.
- W4308482364 isRetracted "false" @default.
- W4308482364 workType "article" @default.