Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208449583> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3208449583 abstract "Federated Learning is a framework that jointly trains a model textit{with} complete knowledge on a remotely placed centralized server, but textit{without} the requirement of accessing the data stored in distributed machines. Some work assumes that the data generated from edge devices are identically and independently sampled from a common population distribution. However, such ideal sampling may not be realistic in many contexts. Also, models based on intrinsic agency, such as active sampling schemes, may lead to highly biased sampling. So an imminent question is how robust Federated Learning is to biased sampling? In this workfootnote{url{https://github.com/jiaqian/robustness_of_FL}}, we experimentally investigate two such scenarios. First, we study a centralized classifier aggregated from a collection of local classifiers trained with data having categorical heterogeneity. Second, we study a classifier aggregated from a collection of local classifiers trained by data through active sampling at the edge. We present evidence in both scenarios that Federated Learning is robust to data heterogeneity when local training iterations and communication frequency are appropriately chosen." @default.
- W3208449583 created "2021-11-08" @default.
- W3208449583 creator A5018292103 @default.
- W3208449583 creator A5018416804 @default.
- W3208449583 creator A5024893234 @default.
- W3208449583 creator A5026065808 @default.
- W3208449583 creator A5082046789 @default.
- W3208449583 date "2021-11-02" @default.
- W3208449583 modified "2023-10-16" @default.
- W3208449583 title "Robustness Analytics to Data Heterogeneity in Edge Computing" @default.
- W3208449583 cites W2088068024 @default.
- W3208449583 cites W2095705004 @default.
- W3208449583 cites W2140136927 @default.
- W3208449583 cites W2143194472 @default.
- W3208449583 cites W2144513243 @default.
- W3208449583 cites W2210596465 @default.
- W3208449583 cites W2535838896 @default.
- W3208449583 cites W2752291283 @default.
- W3208449583 cites W2773246426 @default.
- W3208449583 cites W2807006176 @default.
- W3208449583 cites W2918607134 @default.
- W3208449583 cites W2949117887 @default.
- W3208449583 cites W2954070046 @default.
- W3208449583 cites W2955011752 @default.
- W3208449583 cites W2963238274 @default.
- W3208449583 cites W2963818033 @default.
- W3208449583 cites W2970291982 @default.
- W3208449583 cites W2977884619 @default.
- W3208449583 cites W2980046802 @default.
- W3208449583 cites W2995022099 @default.
- W3208449583 cites W3006740354 @default.
- W3208449583 cites W3092543157 @default.
- W3208449583 cites W3105122387 @default.
- W3208449583 cites W605727707 @default.
- W3208449583 doi "https://doi.org/10.5281/zenodo.5856410" @default.
- W3208449583 hasPublicationYear "2021" @default.
- W3208449583 type Work @default.
- W3208449583 sameAs 3208449583 @default.
- W3208449583 citedByCount "0" @default.
- W3208449583 crossrefType "journal-article" @default.
- W3208449583 hasAuthorship W3208449583A5018292103 @default.
- W3208449583 hasAuthorship W3208449583A5018416804 @default.
- W3208449583 hasAuthorship W3208449583A5024893234 @default.
- W3208449583 hasAuthorship W3208449583A5026065808 @default.
- W3208449583 hasAuthorship W3208449583A5082046789 @default.
- W3208449583 hasBestOaLocation W32084495831 @default.
- W3208449583 hasConcept C104317684 @default.
- W3208449583 hasConcept C124101348 @default.
- W3208449583 hasConcept C154945302 @default.
- W3208449583 hasConcept C162307627 @default.
- W3208449583 hasConcept C175801342 @default.
- W3208449583 hasConcept C185592680 @default.
- W3208449583 hasConcept C2522767166 @default.
- W3208449583 hasConcept C41008148 @default.
- W3208449583 hasConcept C55493867 @default.
- W3208449583 hasConcept C63479239 @default.
- W3208449583 hasConcept C79158427 @default.
- W3208449583 hasConceptScore W3208449583C104317684 @default.
- W3208449583 hasConceptScore W3208449583C124101348 @default.
- W3208449583 hasConceptScore W3208449583C154945302 @default.
- W3208449583 hasConceptScore W3208449583C162307627 @default.
- W3208449583 hasConceptScore W3208449583C175801342 @default.
- W3208449583 hasConceptScore W3208449583C185592680 @default.
- W3208449583 hasConceptScore W3208449583C2522767166 @default.
- W3208449583 hasConceptScore W3208449583C41008148 @default.
- W3208449583 hasConceptScore W3208449583C55493867 @default.
- W3208449583 hasConceptScore W3208449583C63479239 @default.
- W3208449583 hasConceptScore W3208449583C79158427 @default.
- W3208449583 hasLocation W32084495831 @default.
- W3208449583 hasLocation W32084495832 @default.
- W3208449583 hasLocation W32084495833 @default.
- W3208449583 hasLocation W32084495834 @default.
- W3208449583 hasLocation W32084495835 @default.
- W3208449583 hasLocation W32084495836 @default.
- W3208449583 hasOpenAccess W3208449583 @default.
- W3208449583 hasPrimaryLocation W32084495831 @default.
- W3208449583 hasRelatedWork W2413477332 @default.
- W3208449583 hasRelatedWork W2508885301 @default.
- W3208449583 hasRelatedWork W2777139086 @default.
- W3208449583 hasRelatedWork W2794907032 @default.
- W3208449583 hasRelatedWork W3092201768 @default.
- W3208449583 hasRelatedWork W3123108850 @default.
- W3208449583 hasRelatedWork W4226266853 @default.
- W3208449583 hasRelatedWork W4239839666 @default.
- W3208449583 hasRelatedWork W4297840273 @default.
- W3208449583 hasRelatedWork W2551093110 @default.
- W3208449583 isParatext "false" @default.
- W3208449583 isRetracted "false" @default.
- W3208449583 magId "3208449583" @default.
- W3208449583 workType "article" @default.