Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367333175> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4367333175 endingPage "42095" @default.
- W4367333175 startingPage "42082" @default.
- W4367333175 abstract "As contemporary systems are being operated in dynamic situations alternating into decentralized and distributed environments from conventional centralized frameworks, Federated Learning (FL) has been gaining attention for an effective architecture when aggregating the information and correspondingly trained AI model of geographically distributed datasets. However, the convergence of FL suffers from the skewed and biased non-IID local dataset acquired from the heterogeneous environment, which is common in real-world practice. To address this issue, we propose a novel Label-wise clustering algorithm in FL (FedLC) that guarantees the convergence among local clients that hold unique distribution. We theoretically analyze the non-IID attributes that potentially affect the performance, defining the six non-IID scenarios in hierarchical order. Through conducting experiments on the suggested non-IID scenarios, we empirically show that the vanilla FL aggregation model is incapable of gaining stable convergence, generating a biased model. By pre-evaluating the local dataset prior to training models, FedLC determines the potential contributions with respect to trainability in a global view, and adaptively selects the locals to collaboratively take part in while aggregation. Our experimental results show that the FedLC outperforms the state-of-the-art non-IID FL optimization studies, offering a robust convergence in a highly skewed and biased non-IID dataset." @default.
- W4367333175 created "2023-04-30" @default.
- W4367333175 creator A5017173347 @default.
- W4367333175 creator A5035093564 @default.
- W4367333175 date "2023-01-01" @default.
- W4367333175 modified "2023-09-26" @default.
- W4367333175 title "FedLC: Optimizing Federated Learning in Non-IID Data via Label-Wise Clustering" @default.
- W4367333175 cites W2553156677 @default.
- W4367333175 cites W3080934299 @default.
- W4367333175 cites W3091635927 @default.
- W4367333175 cites W3095540342 @default.
- W4367333175 cites W3100779497 @default.
- W4367333175 cites W3104631511 @default.
- W4367333175 cites W3130042795 @default.
- W4367333175 cites W3135231128 @default.
- W4367333175 cites W3137605545 @default.
- W4367333175 cites W3163280978 @default.
- W4367333175 cites W3174401204 @default.
- W4367333175 cites W3178875373 @default.
- W4367333175 cites W3182125009 @default.
- W4367333175 cites W3191604281 @default.
- W4367333175 cites W3193107436 @default.
- W4367333175 cites W3198939852 @default.
- W4367333175 cites W3213321731 @default.
- W4367333175 cites W4200598890 @default.
- W4367333175 cites W4206731046 @default.
- W4367333175 cites W4226461837 @default.
- W4367333175 cites W4229029907 @default.
- W4367333175 cites W4281753687 @default.
- W4367333175 cites W4294733424 @default.
- W4367333175 cites W4297794693 @default.
- W4367333175 doi "https://doi.org/10.1109/access.2023.3271517" @default.
- W4367333175 hasPublicationYear "2023" @default.
- W4367333175 type Work @default.
- W4367333175 citedByCount "0" @default.
- W4367333175 crossrefType "journal-article" @default.
- W4367333175 hasAuthorship W4367333175A5017173347 @default.
- W4367333175 hasAuthorship W4367333175A5035093564 @default.
- W4367333175 hasBestOaLocation W43673331751 @default.
- W4367333175 hasConcept C119857082 @default.
- W4367333175 hasConcept C124101348 @default.
- W4367333175 hasConcept C154945302 @default.
- W4367333175 hasConcept C162324750 @default.
- W4367333175 hasConcept C2777303404 @default.
- W4367333175 hasConcept C2992525071 @default.
- W4367333175 hasConcept C41008148 @default.
- W4367333175 hasConcept C50522688 @default.
- W4367333175 hasConcept C73555534 @default.
- W4367333175 hasConceptScore W4367333175C119857082 @default.
- W4367333175 hasConceptScore W4367333175C124101348 @default.
- W4367333175 hasConceptScore W4367333175C154945302 @default.
- W4367333175 hasConceptScore W4367333175C162324750 @default.
- W4367333175 hasConceptScore W4367333175C2777303404 @default.
- W4367333175 hasConceptScore W4367333175C2992525071 @default.
- W4367333175 hasConceptScore W4367333175C41008148 @default.
- W4367333175 hasConceptScore W4367333175C50522688 @default.
- W4367333175 hasConceptScore W4367333175C73555534 @default.
- W4367333175 hasFunder F4320322093 @default.
- W4367333175 hasLocation W43673331751 @default.
- W4367333175 hasOpenAccess W4367333175 @default.
- W4367333175 hasPrimaryLocation W43673331751 @default.
- W4367333175 hasRelatedWork W2961085424 @default.
- W4367333175 hasRelatedWork W3046775127 @default.
- W4367333175 hasRelatedWork W3170094116 @default.
- W4367333175 hasRelatedWork W4205958290 @default.
- W4367333175 hasRelatedWork W4285260836 @default.
- W4367333175 hasRelatedWork W4286629047 @default.
- W4367333175 hasRelatedWork W4306321456 @default.
- W4367333175 hasRelatedWork W4306674287 @default.
- W4367333175 hasRelatedWork W4386462264 @default.
- W4367333175 hasRelatedWork W4224009465 @default.
- W4367333175 hasVolume "11" @default.
- W4367333175 isParatext "false" @default.
- W4367333175 isRetracted "false" @default.
- W4367333175 workType "article" @default.