Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198563652> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W3198563652 endingPage "486" @default.
- W3198563652 startingPage "480" @default.
- W3198563652 abstract "Federated learning (FL) is an emerging distributed machine learning paradigm that avoids data sharing among training nodes so as to protect data privacy. Under the coordination of the FL server, each client conducts model training using its own computing resource and private data set. The global model can be created by aggregating the training results of clients. To cope with highly non-IID data distributions, personalized federated learning (PFL) has been proposed to improve overall performance by allowing each client to learn a personalized model. However, one major drawback of a personalized model is the loss of generalization. To achieve model personalization while maintaining better generalization, in this paper, we propose a new approach, named PFL-MoE, which mixes outputs of the personalized model and global model via the MoE architecture. PFL-MoE is a generic approach and can be instantiated by integrating existing PFL algorithms. Particularly, we propose the PFL-MF algorithm which is an instance of PFL-MoE based on the freeze-base PFL algorithm. We further improve PFL-MF by enhancing the decision-making ability of MoE gating network and propose a variant algorithm PFL-MFE. We demonstrate the effectiveness of PFL-MoE by training the LeNet-5 and VGG-16 models on the Fashion-MNIST and CIFAR-10 datasets with non-IID partitions." @default.
- W3198563652 created "2021-09-13" @default.
- W3198563652 creator A5023890889 @default.
- W3198563652 creator A5041031990 @default.
- W3198563652 creator A5083081879 @default.
- W3198563652 creator A5084826798 @default.
- W3198563652 date "2021-01-01" @default.
- W3198563652 modified "2023-10-16" @default.
- W3198563652 title "PFL-MoE: Personalized Federated Learning Based on Mixture of Experts" @default.
- W3198563652 cites W2541884796 @default.
- W3198563652 cites W2972570881 @default.
- W3198563652 cites W2994947228 @default.
- W3198563652 cites W3006157707 @default.
- W3198563652 cites W3099314130 @default.
- W3198563652 doi "https://doi.org/10.1007/978-3-030-85896-4_37" @default.
- W3198563652 hasPublicationYear "2021" @default.
- W3198563652 type Work @default.
- W3198563652 sameAs 3198563652 @default.
- W3198563652 citedByCount "2" @default.
- W3198563652 countsByYear W31985636522021 @default.
- W3198563652 countsByYear W31985636522022 @default.
- W3198563652 crossrefType "book-chapter" @default.
- W3198563652 hasAuthorship W3198563652A5023890889 @default.
- W3198563652 hasAuthorship W3198563652A5041031990 @default.
- W3198563652 hasAuthorship W3198563652A5083081879 @default.
- W3198563652 hasAuthorship W3198563652A5084826798 @default.
- W3198563652 hasBestOaLocation W31985636522 @default.
- W3198563652 hasConcept C41008148 @default.
- W3198563652 hasConceptScore W3198563652C41008148 @default.
- W3198563652 hasLocation W31985636521 @default.
- W3198563652 hasLocation W31985636522 @default.
- W3198563652 hasOpenAccess W3198563652 @default.
- W3198563652 hasPrimaryLocation W31985636521 @default.
- W3198563652 hasRelatedWork W2049775471 @default.
- W3198563652 hasRelatedWork W2093578348 @default.
- W3198563652 hasRelatedWork W2350741829 @default.
- W3198563652 hasRelatedWork W2358668433 @default.
- W3198563652 hasRelatedWork W2376932109 @default.
- W3198563652 hasRelatedWork W2382290278 @default.
- W3198563652 hasRelatedWork W2390279801 @default.
- W3198563652 hasRelatedWork W2748952813 @default.
- W3198563652 hasRelatedWork W2899084033 @default.
- W3198563652 hasRelatedWork W3004735627 @default.
- W3198563652 isParatext "false" @default.
- W3198563652 isRetracted "false" @default.
- W3198563652 magId "3198563652" @default.
- W3198563652 workType "book-chapter" @default.