Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377235461> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4377235461 endingPage "17" @default.
- W4377235461 startingPage "1" @default.
- W4377235461 abstract "Generative adversarial networks (GANs) have been advancing and gaining tremendous interests from both academia and industry. With the development of wireless technologies, a huge amount of data generated at the network edge provides an unprecedented opportunity to develop GANs applications. However, due to the constraints such as bandwidth, privacy, and legal issues, it is inappropriate to collect and send all data to the cloud or servers for analysis, training, and mining. Thus, deploying and training GANs at the edge becomes a promising alternative solution. The instability of GANs introduced by non-independent and identical data (Non-IID) poses significant challenges to training GANs. To address these challenges, this paper presents a novel federated learning framework for GANs, namely, <underline xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>C</u> ollaborated g <underline xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>A</u> me <underline xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>P</u> arallel Learning (CAP). CAP supports parallel training of data and models for GANs, breaking the isolated training among generators that exists in the previous distributed algorithms, and achieving collaborative learning among cloud, edge servers, and devices. Then, to further enhance the ability of CAP-GAN for addressing Non-IID issues, we propose a Mix-Generator module (Mix-G) which divides a generator into the sharing layer and personalizing layer. The Mix-G module extracts the generic and personalization features and improves the performance of CAP-GAN on extremely personalizing datasets. Experimental results and analysis substantiate the usefulness and superiority of our proposed CAP-GAN scheme which can achieve better results in the Non-IID scenarios compared with the state-of-the-art algorithms." @default.
- W4377235461 created "2023-05-23" @default.
- W4377235461 creator A5015993565 @default.
- W4377235461 creator A5017770533 @default.
- W4377235461 creator A5023246930 @default.
- W4377235461 creator A5061568038 @default.
- W4377235461 creator A5076994242 @default.
- W4377235461 creator A5083702949 @default.
- W4377235461 date "2023-01-01" @default.
- W4377235461 modified "2023-10-06" @default.
- W4377235461 title "A Novel Federated Learning Scheme for Generative Adversarial Networks" @default.
- W4377235461 doi "https://doi.org/10.1109/tmc.2023.3278668" @default.
- W4377235461 hasPublicationYear "2023" @default.
- W4377235461 type Work @default.
- W4377235461 citedByCount "1" @default.
- W4377235461 countsByYear W43772354612023 @default.
- W4377235461 crossrefType "journal-article" @default.
- W4377235461 hasAuthorship W4377235461A5015993565 @default.
- W4377235461 hasAuthorship W4377235461A5017770533 @default.
- W4377235461 hasAuthorship W4377235461A5023246930 @default.
- W4377235461 hasAuthorship W4377235461A5061568038 @default.
- W4377235461 hasAuthorship W4377235461A5076994242 @default.
- W4377235461 hasAuthorship W4377235461A5083702949 @default.
- W4377235461 hasBestOaLocation W43772354612 @default.
- W4377235461 hasConcept C111919701 @default.
- W4377235461 hasConcept C119857082 @default.
- W4377235461 hasConcept C121332964 @default.
- W4377235461 hasConcept C134306372 @default.
- W4377235461 hasConcept C154945302 @default.
- W4377235461 hasConcept C162307627 @default.
- W4377235461 hasConcept C163258240 @default.
- W4377235461 hasConcept C178790620 @default.
- W4377235461 hasConcept C185592680 @default.
- W4377235461 hasConcept C2779227376 @default.
- W4377235461 hasConcept C2780992000 @default.
- W4377235461 hasConcept C31258907 @default.
- W4377235461 hasConcept C33923547 @default.
- W4377235461 hasConcept C37736160 @default.
- W4377235461 hasConcept C39890363 @default.
- W4377235461 hasConcept C41008148 @default.
- W4377235461 hasConcept C62520636 @default.
- W4377235461 hasConcept C77618280 @default.
- W4377235461 hasConcept C79974875 @default.
- W4377235461 hasConcept C93996380 @default.
- W4377235461 hasConceptScore W4377235461C111919701 @default.
- W4377235461 hasConceptScore W4377235461C119857082 @default.
- W4377235461 hasConceptScore W4377235461C121332964 @default.
- W4377235461 hasConceptScore W4377235461C134306372 @default.
- W4377235461 hasConceptScore W4377235461C154945302 @default.
- W4377235461 hasConceptScore W4377235461C162307627 @default.
- W4377235461 hasConceptScore W4377235461C163258240 @default.
- W4377235461 hasConceptScore W4377235461C178790620 @default.
- W4377235461 hasConceptScore W4377235461C185592680 @default.
- W4377235461 hasConceptScore W4377235461C2779227376 @default.
- W4377235461 hasConceptScore W4377235461C2780992000 @default.
- W4377235461 hasConceptScore W4377235461C31258907 @default.
- W4377235461 hasConceptScore W4377235461C33923547 @default.
- W4377235461 hasConceptScore W4377235461C37736160 @default.
- W4377235461 hasConceptScore W4377235461C39890363 @default.
- W4377235461 hasConceptScore W4377235461C41008148 @default.
- W4377235461 hasConceptScore W4377235461C62520636 @default.
- W4377235461 hasConceptScore W4377235461C77618280 @default.
- W4377235461 hasConceptScore W4377235461C79974875 @default.
- W4377235461 hasConceptScore W4377235461C93996380 @default.
- W4377235461 hasLocation W43772354611 @default.
- W4377235461 hasLocation W43772354612 @default.
- W4377235461 hasOpenAccess W4377235461 @default.
- W4377235461 hasPrimaryLocation W43772354611 @default.
- W4377235461 hasRelatedWork W2476099471 @default.
- W4377235461 hasRelatedWork W2561036008 @default.
- W4377235461 hasRelatedWork W2914998939 @default.
- W4377235461 hasRelatedWork W3005996785 @default.
- W4377235461 hasRelatedWork W3006227554 @default.
- W4377235461 hasRelatedWork W3156291593 @default.
- W4377235461 hasRelatedWork W3198184493 @default.
- W4377235461 hasRelatedWork W4220812973 @default.
- W4377235461 hasRelatedWork W4289303600 @default.
- W4377235461 hasRelatedWork W4386984417 @default.
- W4377235461 isParatext "false" @default.
- W4377235461 isRetracted "false" @default.
- W4377235461 workType "article" @default.