Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366250293> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4366250293 abstract "Federated learning (FL) enables large amounts of participants to construct a global learning model, while storing training data privately at local client devices. A fundamental issue in FL systems is the susceptibility to the highly skewed distributed data. A series of methods have been proposed to mitigate the Non-IID problem by limiting the distances between local models and the global model, but they cannot address the root cause of skewed data distribution eventually. Some methods share extra samples from the server to clients, which requires comprehensive data collection by the server and may raise potential privacy risks. In this work, we propose an efficient and adaptive framework, named Generative Federated Learning (GFL), to solve the skewed data problem in FL systems in a privacy-friendly way. We introduce Generative Adversarial Networks (GAN) into FL to generate synthetic data, which can be used by the server to balance data distributions. To keep the distribution and membership of clients' data private, the synthetic samples are generated with random distributions and protected by a differential privacy mechanism. The results show that GFL significantly outperforms existing approaches in terms of achieving more accurate global models (e.g., 17% - 50% higher accuracy) as well as building global models with faster convergence speed without increasing much computation or communication costs." @default.
- W4366250293 created "2023-04-20" @default.
- W4366250293 creator A5000173131 @default.
- W4366250293 creator A5003547177 @default.
- W4366250293 creator A5006612493 @default.
- W4366250293 date "2023-03-13" @default.
- W4366250293 modified "2023-10-16" @default.
- W4366250293 title "GFL: Federated Learning on Non-IID Data via Privacy-Preserving Synthetic Data" @default.
- W4366250293 cites W2194775991 @default.
- W4366250293 cites W2535690855 @default.
- W4366250293 cites W2734358244 @default.
- W4366250293 cites W2795435272 @default.
- W4366250293 cites W2887995258 @default.
- W4366250293 cites W2903890850 @default.
- W4366250293 cites W2911978475 @default.
- W4366250293 cites W2922569945 @default.
- W4366250293 cites W2963278610 @default.
- W4366250293 cites W2973232880 @default.
- W4366250293 cites W2997721570 @default.
- W4366250293 cites W3015598833 @default.
- W4366250293 cites W3021026170 @default.
- W4366250293 cites W3157242219 @default.
- W4366250293 cites W3193908336 @default.
- W4366250293 cites W4207054595 @default.
- W4366250293 cites W4226225515 @default.
- W4366250293 cites W4308410741 @default.
- W4366250293 doi "https://doi.org/10.1109/percom56429.2023.10099110" @default.
- W4366250293 hasPublicationYear "2023" @default.
- W4366250293 type Work @default.
- W4366250293 citedByCount "1" @default.
- W4366250293 countsByYear W43662502932023 @default.
- W4366250293 crossrefType "proceedings-article" @default.
- W4366250293 hasAuthorship W4366250293A5000173131 @default.
- W4366250293 hasAuthorship W4366250293A5003547177 @default.
- W4366250293 hasAuthorship W4366250293A5006612493 @default.
- W4366250293 hasConcept C119857082 @default.
- W4366250293 hasConcept C123201435 @default.
- W4366250293 hasConcept C124101348 @default.
- W4366250293 hasConcept C154945302 @default.
- W4366250293 hasConcept C160920958 @default.
- W4366250293 hasConcept C162324750 @default.
- W4366250293 hasConcept C167966045 @default.
- W4366250293 hasConcept C23130292 @default.
- W4366250293 hasConcept C2777303404 @default.
- W4366250293 hasConcept C2780801425 @default.
- W4366250293 hasConcept C2992525071 @default.
- W4366250293 hasConcept C31258907 @default.
- W4366250293 hasConcept C38652104 @default.
- W4366250293 hasConcept C39890363 @default.
- W4366250293 hasConcept C41008148 @default.
- W4366250293 hasConcept C50522688 @default.
- W4366250293 hasConcept C67186912 @default.
- W4366250293 hasConcept C77088390 @default.
- W4366250293 hasConcept C80444323 @default.
- W4366250293 hasConcept C93996380 @default.
- W4366250293 hasConceptScore W4366250293C119857082 @default.
- W4366250293 hasConceptScore W4366250293C123201435 @default.
- W4366250293 hasConceptScore W4366250293C124101348 @default.
- W4366250293 hasConceptScore W4366250293C154945302 @default.
- W4366250293 hasConceptScore W4366250293C160920958 @default.
- W4366250293 hasConceptScore W4366250293C162324750 @default.
- W4366250293 hasConceptScore W4366250293C167966045 @default.
- W4366250293 hasConceptScore W4366250293C23130292 @default.
- W4366250293 hasConceptScore W4366250293C2777303404 @default.
- W4366250293 hasConceptScore W4366250293C2780801425 @default.
- W4366250293 hasConceptScore W4366250293C2992525071 @default.
- W4366250293 hasConceptScore W4366250293C31258907 @default.
- W4366250293 hasConceptScore W4366250293C38652104 @default.
- W4366250293 hasConceptScore W4366250293C39890363 @default.
- W4366250293 hasConceptScore W4366250293C41008148 @default.
- W4366250293 hasConceptScore W4366250293C50522688 @default.
- W4366250293 hasConceptScore W4366250293C67186912 @default.
- W4366250293 hasConceptScore W4366250293C77088390 @default.
- W4366250293 hasConceptScore W4366250293C80444323 @default.
- W4366250293 hasConceptScore W4366250293C93996380 @default.
- W4366250293 hasLocation W43662502931 @default.
- W4366250293 hasOpenAccess W4366250293 @default.
- W4366250293 hasPrimaryLocation W43662502931 @default.
- W4366250293 hasRelatedWork W3011958316 @default.
- W4366250293 hasRelatedWork W3131298545 @default.
- W4366250293 hasRelatedWork W3132610544 @default.
- W4366250293 hasRelatedWork W3176736928 @default.
- W4366250293 hasRelatedWork W4214940550 @default.
- W4366250293 hasRelatedWork W4360765041 @default.
- W4366250293 hasRelatedWork W4366250293 @default.
- W4366250293 hasRelatedWork W4366307888 @default.
- W4366250293 hasRelatedWork W4378192368 @default.
- W4366250293 hasRelatedWork W4383469366 @default.
- W4366250293 isParatext "false" @default.
- W4366250293 isRetracted "false" @default.
- W4366250293 workType "article" @default.