Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384705344> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4384705344 abstract "Federated Learning (FL) constructs a distributed machine learning framework that involves multiple remote clients collaboratively training models. However in real-world situations, the emergence of non-Independent and Identically Distributed (non-IID) data makes the global model generated by traditional FL algorithms no longer meet the needs of all clients, and the accuracy is greatly reduced. In this paper, we propose a personalized federated multi-task learning method via similarity awareness (PFedSA), which captures the similarity between client data through model parameters uploaded by clients, thus facilitating collaborative training of similar clients and providing personalized models based on each client’s data distribution. Specifically, it generates the intrinsic cluster structure among clients and introduces personalized patch layers into the cluster to personalize the cluster model. PFedSA also maintains the generalization ability of models, which allows each client to benefit from nodes with similar data distributions when training data, and the greater the similarity, the more benefit. We evaluate the performance of the PFedSA method using MNIST, EMNIST and CIFAR10 datasets, and investigate the impact of different data setting schemes on the performance of PFedSA. The results show that in all data setting scenarios, the PFedSA method proposed in this paper can achieve the best personalization performance, having more clients with higher accuracy, and it is especially effective when the client’s data is non-IID." @default.
- W4384705344 created "2023-07-20" @default.
- W4384705344 creator A5020182983 @default.
- W4384705344 creator A5027592431 @default.
- W4384705344 creator A5040815411 @default.
- W4384705344 creator A5057698640 @default.
- W4384705344 date "2023-05-01" @default.
- W4384705344 modified "2023-09-26" @default.
- W4384705344 title "PFedSA: Personalized Federated Multi-Task Learning via Similarity Awareness" @default.
- W4384705344 cites W2007339694 @default.
- W4384705344 cites W2619606157 @default.
- W4384705344 cites W2734358244 @default.
- W4384705344 cites W2912213068 @default.
- W4384705344 cites W3012549930 @default.
- W4384705344 cites W3034896171 @default.
- W4384705344 cites W3051272477 @default.
- W4384705344 cites W3080934299 @default.
- W4384705344 cites W3091635927 @default.
- W4384705344 cites W3103802018 @default.
- W4384705344 cites W3112044954 @default.
- W4384705344 cites W3174401204 @default.
- W4384705344 cites W3186051974 @default.
- W4384705344 cites W3196371845 @default.
- W4384705344 cites W3211781253 @default.
- W4384705344 doi "https://doi.org/10.1109/ipdps54959.2023.00055" @default.
- W4384705344 hasPublicationYear "2023" @default.
- W4384705344 type Work @default.
- W4384705344 citedByCount "0" @default.
- W4384705344 crossrefType "proceedings-article" @default.
- W4384705344 hasAuthorship W4384705344A5020182983 @default.
- W4384705344 hasAuthorship W4384705344A5027592431 @default.
- W4384705344 hasAuthorship W4384705344A5040815411 @default.
- W4384705344 hasAuthorship W4384705344A5057698640 @default.
- W4384705344 hasConcept C103278499 @default.
- W4384705344 hasConcept C115961682 @default.
- W4384705344 hasConcept C119857082 @default.
- W4384705344 hasConcept C124101348 @default.
- W4384705344 hasConcept C134306372 @default.
- W4384705344 hasConcept C136764020 @default.
- W4384705344 hasConcept C154945302 @default.
- W4384705344 hasConcept C162324750 @default.
- W4384705344 hasConcept C177148314 @default.
- W4384705344 hasConcept C183003079 @default.
- W4384705344 hasConcept C187736073 @default.
- W4384705344 hasConcept C190502265 @default.
- W4384705344 hasConcept C2780451532 @default.
- W4384705344 hasConcept C33923547 @default.
- W4384705344 hasConcept C41008148 @default.
- W4384705344 hasConcept C50644808 @default.
- W4384705344 hasConcept C67186912 @default.
- W4384705344 hasConcept C71901391 @default.
- W4384705344 hasConcept C77088390 @default.
- W4384705344 hasConceptScore W4384705344C103278499 @default.
- W4384705344 hasConceptScore W4384705344C115961682 @default.
- W4384705344 hasConceptScore W4384705344C119857082 @default.
- W4384705344 hasConceptScore W4384705344C124101348 @default.
- W4384705344 hasConceptScore W4384705344C134306372 @default.
- W4384705344 hasConceptScore W4384705344C136764020 @default.
- W4384705344 hasConceptScore W4384705344C154945302 @default.
- W4384705344 hasConceptScore W4384705344C162324750 @default.
- W4384705344 hasConceptScore W4384705344C177148314 @default.
- W4384705344 hasConceptScore W4384705344C183003079 @default.
- W4384705344 hasConceptScore W4384705344C187736073 @default.
- W4384705344 hasConceptScore W4384705344C190502265 @default.
- W4384705344 hasConceptScore W4384705344C2780451532 @default.
- W4384705344 hasConceptScore W4384705344C33923547 @default.
- W4384705344 hasConceptScore W4384705344C41008148 @default.
- W4384705344 hasConceptScore W4384705344C50644808 @default.
- W4384705344 hasConceptScore W4384705344C67186912 @default.
- W4384705344 hasConceptScore W4384705344C71901391 @default.
- W4384705344 hasConceptScore W4384705344C77088390 @default.
- W4384705344 hasFunder F4320321001 @default.
- W4384705344 hasLocation W43847053441 @default.
- W4384705344 hasOpenAccess W4384705344 @default.
- W4384705344 hasPrimaryLocation W43847053441 @default.
- W4384705344 hasRelatedWork W2039503904 @default.
- W4384705344 hasRelatedWork W2597787948 @default.
- W4384705344 hasRelatedWork W2791952757 @default.
- W4384705344 hasRelatedWork W2951786554 @default.
- W4384705344 hasRelatedWork W2978290780 @default.
- W4384705344 hasRelatedWork W2979907025 @default.
- W4384705344 hasRelatedWork W3132360532 @default.
- W4384705344 hasRelatedWork W3186840088 @default.
- W4384705344 hasRelatedWork W4312120628 @default.
- W4384705344 hasRelatedWork W4320853675 @default.
- W4384705344 isParatext "false" @default.
- W4384705344 isRetracted "false" @default.
- W4384705344 workType "article" @default.