Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288336939> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4288336939 abstract "The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates. Server-based solutions are prone to the problem of a single-point-of-failure. In this respect, collaborative learning frameworks, such as federated learning (FL), are more robust. Existing federated learning frameworks overlook an important aspect of participation: fairness. All parties are given the same final model without regard to their contributions. To address these issues, we propose a decentralized Fair and Privacy-Preserving Deep Learning (FPPDL) framework to incorporate fairness into federated deep learning models. In particular, we design a local credibility mutual evaluation mechanism to guarantee fairness, and a three-layer onion-style encryption scheme to guarantee both accuracy and privacy. Different from existing FL paradigm, under FPPDL, each participant receives a different version of the FL model with performance commensurate with his contributions. Experiments on benchmark datasets demonstrate that FPPDL balances fairness, privacy and accuracy. It enables federated learning ecosystems to detect and isolate low-contribution parties, thereby promoting responsible participation." @default.
- W4288336939 created "2022-07-29" @default.
- W4288336939 creator A5048997284 @default.
- W4288336939 creator A5052577882 @default.
- W4288336939 creator A5059676452 @default.
- W4288336939 creator A5059845740 @default.
- W4288336939 creator A5060534829 @default.
- W4288336939 creator A5078711649 @default.
- W4288336939 creator A5080328538 @default.
- W4288336939 creator A5091448543 @default.
- W4288336939 date "2019-06-03" @default.
- W4288336939 modified "2023-09-26" @default.
- W4288336939 title "Towards Fair and Privacy-Preserving Federated Deep Models" @default.
- W4288336939 doi "https://doi.org/10.48550/arxiv.1906.01167" @default.
- W4288336939 hasPublicationYear "2019" @default.
- W4288336939 type Work @default.
- W4288336939 citedByCount "0" @default.
- W4288336939 crossrefType "posted-content" @default.
- W4288336939 hasAuthorship W4288336939A5048997284 @default.
- W4288336939 hasAuthorship W4288336939A5052577882 @default.
- W4288336939 hasAuthorship W4288336939A5059676452 @default.
- W4288336939 hasAuthorship W4288336939A5059845740 @default.
- W4288336939 hasAuthorship W4288336939A5060534829 @default.
- W4288336939 hasAuthorship W4288336939A5078711649 @default.
- W4288336939 hasAuthorship W4288336939A5080328538 @default.
- W4288336939 hasAuthorship W4288336939A5091448543 @default.
- W4288336939 hasBestOaLocation W42883369391 @default.
- W4288336939 hasConcept C108583219 @default.
- W4288336939 hasConcept C120314980 @default.
- W4288336939 hasConcept C13280743 @default.
- W4288336939 hasConcept C134306372 @default.
- W4288336939 hasConcept C148730421 @default.
- W4288336939 hasConcept C154945302 @default.
- W4288336939 hasConcept C15744967 @default.
- W4288336939 hasConcept C165136773 @default.
- W4288336939 hasConcept C17744445 @default.
- W4288336939 hasConcept C185798385 @default.
- W4288336939 hasConcept C19417346 @default.
- W4288336939 hasConcept C199539241 @default.
- W4288336939 hasConcept C205649164 @default.
- W4288336939 hasConcept C22019652 @default.
- W4288336939 hasConcept C2779582901 @default.
- W4288336939 hasConcept C2780224610 @default.
- W4288336939 hasConcept C2992525071 @default.
- W4288336939 hasConcept C33923547 @default.
- W4288336939 hasConcept C38652104 @default.
- W4288336939 hasConcept C41008148 @default.
- W4288336939 hasConcept C50644808 @default.
- W4288336939 hasConcept C77618280 @default.
- W4288336939 hasConceptScore W4288336939C108583219 @default.
- W4288336939 hasConceptScore W4288336939C120314980 @default.
- W4288336939 hasConceptScore W4288336939C13280743 @default.
- W4288336939 hasConceptScore W4288336939C134306372 @default.
- W4288336939 hasConceptScore W4288336939C148730421 @default.
- W4288336939 hasConceptScore W4288336939C154945302 @default.
- W4288336939 hasConceptScore W4288336939C15744967 @default.
- W4288336939 hasConceptScore W4288336939C165136773 @default.
- W4288336939 hasConceptScore W4288336939C17744445 @default.
- W4288336939 hasConceptScore W4288336939C185798385 @default.
- W4288336939 hasConceptScore W4288336939C19417346 @default.
- W4288336939 hasConceptScore W4288336939C199539241 @default.
- W4288336939 hasConceptScore W4288336939C205649164 @default.
- W4288336939 hasConceptScore W4288336939C22019652 @default.
- W4288336939 hasConceptScore W4288336939C2779582901 @default.
- W4288336939 hasConceptScore W4288336939C2780224610 @default.
- W4288336939 hasConceptScore W4288336939C2992525071 @default.
- W4288336939 hasConceptScore W4288336939C33923547 @default.
- W4288336939 hasConceptScore W4288336939C38652104 @default.
- W4288336939 hasConceptScore W4288336939C41008148 @default.
- W4288336939 hasConceptScore W4288336939C50644808 @default.
- W4288336939 hasConceptScore W4288336939C77618280 @default.
- W4288336939 hasLocation W42883369391 @default.
- W4288336939 hasOpenAccess W4288336939 @default.
- W4288336939 hasPrimaryLocation W42883369391 @default.
- W4288336939 hasRelatedWork W3026125222 @default.
- W4288336939 hasRelatedWork W3035162004 @default.
- W4288336939 hasRelatedWork W3099765033 @default.
- W4288336939 hasRelatedWork W3154289258 @default.
- W4288336939 hasRelatedWork W4220996320 @default.
- W4288336939 hasRelatedWork W4285802257 @default.
- W4288336939 hasRelatedWork W4288336939 @default.
- W4288336939 hasRelatedWork W4309224979 @default.
- W4288336939 hasRelatedWork W4313001311 @default.
- W4288336939 hasRelatedWork W4313289428 @default.
- W4288336939 isParatext "false" @default.
- W4288336939 isRetracted "false" @default.
- W4288336939 workType "article" @default.