Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320561017> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4320561017 abstract "In the medical field, multi-center collaborations are often sought to yield more generalizable findings by leveraging the heterogeneity of patient and clinical data. However, recent privacy regulations hinder the possibility to share data, and consequently, to come up with machine learning-based solutions that support diagnosis and prognosis. Federated learning (FL) aims at sidestepping this limitation by bringing AI-based solutions to data owners and only sharing local AI models, or parts thereof, that need then to be aggregated. However, most of the existing federated learning solutions are still at their infancy and show several shortcomings, from the lack of a reliable and effective aggregation scheme able to retain the knowledge learned locally to weak privacy preservation as real data may be reconstructed from model updates. Furthermore, the majority of these approaches, especially those dealing with medical data, relies on a centralized distributed learning strategy that poses robustness, scalability and trust issues. In this paper we present a federated and decentralized learning strategy, FedER, that, exploiting experience replay and generative adversarial concepts, effectively integrates features from local nodes, providing models able to generalize across multiple datasets while maintaining privacy. FedER is tested on two tasks -- tuberculosis and melanoma classification -- using multiple datasets in order to simulate realistic non-i.i.d. medical data scenarios. Results show that our approach achieves performance comparable to standard (non-federated) learning and significantly outperforms state-of-the-art federated methods in their centralized (thus, more favourable) formulation. Code is available at https://github.com/perceivelab/FedER" @default.
- W4320561017 created "2023-02-15" @default.
- W4320561017 creator A5003973109 @default.
- W4320561017 creator A5031450889 @default.
- W4320561017 creator A5033378482 @default.
- W4320561017 creator A5075815307 @default.
- W4320561017 creator A5083136342 @default.
- W4320561017 creator A5085219825 @default.
- W4320561017 creator A5089092418 @default.
- W4320561017 date "2022-06-20" @default.
- W4320561017 modified "2023-10-14" @default.
- W4320561017 title "FedER: Federated Learning through Experience Replay and Privacy-Preserving Data Synthesis" @default.
- W4320561017 doi "https://doi.org/10.48550/arxiv.2206.10048" @default.
- W4320561017 hasPublicationYear "2022" @default.
- W4320561017 type Work @default.
- W4320561017 citedByCount "0" @default.
- W4320561017 crossrefType "posted-content" @default.
- W4320561017 hasAuthorship W4320561017A5003973109 @default.
- W4320561017 hasAuthorship W4320561017A5031450889 @default.
- W4320561017 hasAuthorship W4320561017A5033378482 @default.
- W4320561017 hasAuthorship W4320561017A5075815307 @default.
- W4320561017 hasAuthorship W4320561017A5083136342 @default.
- W4320561017 hasAuthorship W4320561017A5085219825 @default.
- W4320561017 hasAuthorship W4320561017A5089092418 @default.
- W4320561017 hasBestOaLocation W43205610171 @default.
- W4320561017 hasConcept C104317684 @default.
- W4320561017 hasConcept C119857082 @default.
- W4320561017 hasConcept C123201435 @default.
- W4320561017 hasConcept C134306372 @default.
- W4320561017 hasConcept C142724271 @default.
- W4320561017 hasConcept C154945302 @default.
- W4320561017 hasConcept C185592680 @default.
- W4320561017 hasConcept C204787440 @default.
- W4320561017 hasConcept C2779965156 @default.
- W4320561017 hasConcept C2992525071 @default.
- W4320561017 hasConcept C33923547 @default.
- W4320561017 hasConcept C37736160 @default.
- W4320561017 hasConcept C38652104 @default.
- W4320561017 hasConcept C41008148 @default.
- W4320561017 hasConcept C48044578 @default.
- W4320561017 hasConcept C55493867 @default.
- W4320561017 hasConcept C63479239 @default.
- W4320561017 hasConcept C71924100 @default.
- W4320561017 hasConcept C77088390 @default.
- W4320561017 hasConcept C77618280 @default.
- W4320561017 hasConceptScore W4320561017C104317684 @default.
- W4320561017 hasConceptScore W4320561017C119857082 @default.
- W4320561017 hasConceptScore W4320561017C123201435 @default.
- W4320561017 hasConceptScore W4320561017C134306372 @default.
- W4320561017 hasConceptScore W4320561017C142724271 @default.
- W4320561017 hasConceptScore W4320561017C154945302 @default.
- W4320561017 hasConceptScore W4320561017C185592680 @default.
- W4320561017 hasConceptScore W4320561017C204787440 @default.
- W4320561017 hasConceptScore W4320561017C2779965156 @default.
- W4320561017 hasConceptScore W4320561017C2992525071 @default.
- W4320561017 hasConceptScore W4320561017C33923547 @default.
- W4320561017 hasConceptScore W4320561017C37736160 @default.
- W4320561017 hasConceptScore W4320561017C38652104 @default.
- W4320561017 hasConceptScore W4320561017C41008148 @default.
- W4320561017 hasConceptScore W4320561017C48044578 @default.
- W4320561017 hasConceptScore W4320561017C55493867 @default.
- W4320561017 hasConceptScore W4320561017C63479239 @default.
- W4320561017 hasConceptScore W4320561017C71924100 @default.
- W4320561017 hasConceptScore W4320561017C77088390 @default.
- W4320561017 hasConceptScore W4320561017C77618280 @default.
- W4320561017 hasLocation W43205610171 @default.
- W4320561017 hasOpenAccess W4320561017 @default.
- W4320561017 hasPrimaryLocation W43205610171 @default.
- W4320561017 hasRelatedWork W2372762602 @default.
- W4320561017 hasRelatedWork W2610321374 @default.
- W4320561017 hasRelatedWork W3021042056 @default.
- W4320561017 hasRelatedWork W3035168486 @default.
- W4320561017 hasRelatedWork W3035729345 @default.
- W4320561017 hasRelatedWork W3193857078 @default.
- W4320561017 hasRelatedWork W4212792472 @default.
- W4320561017 hasRelatedWork W4298164042 @default.
- W4320561017 hasRelatedWork W4303857474 @default.
- W4320561017 hasRelatedWork W4311734044 @default.
- W4320561017 isParatext "false" @default.
- W4320561017 isRetracted "false" @default.
- W4320561017 workType "article" @default.