Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213802103> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3213802103 endingPage "10" @default.
- W3213802103 startingPage "1" @default.
- W3213802103 abstract "Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence. FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, communication overhead, non-IID (independent and identically distributed) data, and privacy concerns. Training a ML model over heterogeneous non-IID data highly degrades the convergence rate and performance. The existing traditional and clustered FL algorithms exhibit two main limitations, including inefficient client training and static hyperparameter utilization. To overcome these limitations, we propose a novel hybrid algorithm, namely, genetic clustered FL (Genetic CFL), that clusters edge devices based on the training hyperparameters and genetically modifies the parameters clusterwise. Then, we introduce an algorithm that drastically increases the individual cluster accuracy by integrating the density-based clustering and genetic hyperparameter optimization. The results are bench-marked using MNIST handwritten digit dataset and the CIFAR-10 dataset. The proposed genetic CFL shows significant improvements and works well with realistic cases of non-IID and ambiguous data. An accuracy of 99.79% is observed in the MNIST dataset and 76.88% in CIFAR-10 dataset with only 10 training rounds." @default.
- W3213802103 created "2021-11-22" @default.
- W3213802103 creator A5013054905 @default.
- W3213802103 creator A5018409592 @default.
- W3213802103 creator A5024264020 @default.
- W3213802103 creator A5027811562 @default.
- W3213802103 creator A5062525719 @default.
- W3213802103 creator A5064982530 @default.
- W3213802103 date "2021-11-18" @default.
- W3213802103 modified "2023-10-04" @default.
- W3213802103 title "Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning" @default.
- W3213802103 cites W1634912779 @default.
- W3213802103 cites W1971022913 @default.
- W3213802103 cites W1996622927 @default.
- W3213802103 cites W2007339694 @default.
- W3213802103 cites W2140405352 @default.
- W3213802103 cites W2553852618 @default.
- W3213802103 cites W2900594532 @default.
- W3213802103 cites W2967060977 @default.
- W3213802103 cites W2970825779 @default.
- W3213802103 cites W3016169665 @default.
- W3213802103 cites W3091635927 @default.
- W3213802103 cites W3100779497 @default.
- W3213802103 cites W3123459983 @default.
- W3213802103 cites W3125786278 @default.
- W3213802103 cites W3138760940 @default.
- W3213802103 cites W3196370796 @default.
- W3213802103 cites W3202281568 @default.
- W3213802103 cites W3206162503 @default.
- W3213802103 doi "https://doi.org/10.1155/2021/7156420" @default.
- W3213802103 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8616689" @default.
- W3213802103 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34840562" @default.
- W3213802103 hasPublicationYear "2021" @default.
- W3213802103 type Work @default.
- W3213802103 sameAs 3213802103 @default.
- W3213802103 citedByCount "23" @default.
- W3213802103 countsByYear W32138021032022 @default.
- W3213802103 countsByYear W32138021032023 @default.
- W3213802103 crossrefType "journal-article" @default.
- W3213802103 hasAuthorship W3213802103A5013054905 @default.
- W3213802103 hasAuthorship W3213802103A5018409592 @default.
- W3213802103 hasAuthorship W3213802103A5024264020 @default.
- W3213802103 hasAuthorship W3213802103A5027811562 @default.
- W3213802103 hasAuthorship W3213802103A5062525719 @default.
- W3213802103 hasAuthorship W3213802103A5064982530 @default.
- W3213802103 hasBestOaLocation W32138021031 @default.
- W3213802103 hasConcept C111919701 @default.
- W3213802103 hasConcept C119857082 @default.
- W3213802103 hasConcept C124101348 @default.
- W3213802103 hasConcept C154945302 @default.
- W3213802103 hasConcept C162307627 @default.
- W3213802103 hasConcept C190502265 @default.
- W3213802103 hasConcept C2779960059 @default.
- W3213802103 hasConcept C41008148 @default.
- W3213802103 hasConcept C50644808 @default.
- W3213802103 hasConcept C73555534 @default.
- W3213802103 hasConcept C8642999 @default.
- W3213802103 hasConcept C8880873 @default.
- W3213802103 hasConceptScore W3213802103C111919701 @default.
- W3213802103 hasConceptScore W3213802103C119857082 @default.
- W3213802103 hasConceptScore W3213802103C124101348 @default.
- W3213802103 hasConceptScore W3213802103C154945302 @default.
- W3213802103 hasConceptScore W3213802103C162307627 @default.
- W3213802103 hasConceptScore W3213802103C190502265 @default.
- W3213802103 hasConceptScore W3213802103C2779960059 @default.
- W3213802103 hasConceptScore W3213802103C41008148 @default.
- W3213802103 hasConceptScore W3213802103C50644808 @default.
- W3213802103 hasConceptScore W3213802103C73555534 @default.
- W3213802103 hasConceptScore W3213802103C8642999 @default.
- W3213802103 hasConceptScore W3213802103C8880873 @default.
- W3213802103 hasLocation W32138021031 @default.
- W3213802103 hasLocation W32138021032 @default.
- W3213802103 hasLocation W32138021033 @default.
- W3213802103 hasLocation W32138021034 @default.
- W3213802103 hasLocation W32138021035 @default.
- W3213802103 hasLocation W32138021036 @default.
- W3213802103 hasOpenAccess W3213802103 @default.
- W3213802103 hasPrimaryLocation W32138021031 @default.
- W3213802103 hasRelatedWork W2102539288 @default.
- W3213802103 hasRelatedWork W2608595939 @default.
- W3213802103 hasRelatedWork W2919302225 @default.
- W3213802103 hasRelatedWork W2949431720 @default.
- W3213802103 hasRelatedWork W3013823630 @default.
- W3213802103 hasRelatedWork W4210794429 @default.
- W3213802103 hasRelatedWork W4223456145 @default.
- W3213802103 hasRelatedWork W4295309597 @default.
- W3213802103 hasRelatedWork W4297803580 @default.
- W3213802103 hasRelatedWork W4309113015 @default.
- W3213802103 hasVolume "2021" @default.
- W3213802103 isParatext "false" @default.
- W3213802103 isRetracted "false" @default.
- W3213802103 magId "3213802103" @default.
- W3213802103 workType "article" @default.