Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138531978> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3138531978 abstract "The recent advance of the federated learning (FL) has brought new opportunities for privacy-aware distributed machine learning (ML) applications to train a powerful ML model without accessing the private training data of the participants. In this paper, we focus on addressing a novel fair classification problem in FL where the model trained by FL displays discriminatory bias towards particular demographic groups. Addressing the fairness issue in a FL framework posts three critical challenges: fairness and performance trade-offs, restricted information, and constrained coordination. To address these challenges, we develop FairFL, a fair federated learning framework dedicated to reducing the bias in privacy-sensitive ML applications. It consists of a principled deep multi-agent reinforcement learning framework and a secure information aggregation protocol that optimizes both the accuracy and the fairness of the learned model while respecting the strict privacy constraints of the clients. Evaluation results on real-world applications showed that FairFL can achieve significant performance gains in both fairness and accuracy of the learned model compared to state-of-the-art baselines." @default.
- W3138531978 created "2021-03-29" @default.
- W3138531978 creator A5045401193 @default.
- W3138531978 creator A5046454314 @default.
- W3138531978 creator A5073260424 @default.
- W3138531978 date "2020-12-10" @default.
- W3138531978 modified "2023-10-14" @default.
- W3138531978 title "FairFL: A Fair Federated Learning Approach to Reducing Demographic Bias in Privacy-Sensitive Classification Models" @default.
- W3138531978 cites W1641379095 @default.
- W3138531978 cites W2076762727 @default.
- W3138531978 cites W2100960835 @default.
- W3138531978 cites W2155189155 @default.
- W3138531978 cites W2159401786 @default.
- W3138531978 cites W2887866773 @default.
- W3138531978 cites W2905282361 @default.
- W3138531978 cites W2912213068 @default.
- W3138531978 cites W2915575762 @default.
- W3138531978 cites W2946647999 @default.
- W3138531978 cites W2963318081 @default.
- W3138531978 cites W2965366403 @default.
- W3138531978 cites W2982492177 @default.
- W3138531978 cites W2996801518 @default.
- W3138531978 cites W3003191700 @default.
- W3138531978 cites W3006360344 @default.
- W3138531978 cites W3008738665 @default.
- W3138531978 cites W3033991984 @default.
- W3138531978 cites W3034949062 @default.
- W3138531978 cites W3035837967 @default.
- W3138531978 cites W3047024287 @default.
- W3138531978 cites W3101136263 @default.
- W3138531978 cites W3104737638 @default.
- W3138531978 cites W4253271685 @default.
- W3138531978 doi "https://doi.org/10.1109/bigdata50022.2020.9378043" @default.
- W3138531978 hasPublicationYear "2020" @default.
- W3138531978 type Work @default.
- W3138531978 sameAs 3138531978 @default.
- W3138531978 citedByCount "35" @default.
- W3138531978 countsByYear W31385319782021 @default.
- W3138531978 countsByYear W31385319782022 @default.
- W3138531978 countsByYear W31385319782023 @default.
- W3138531978 crossrefType "proceedings-article" @default.
- W3138531978 hasAuthorship W3138531978A5045401193 @default.
- W3138531978 hasAuthorship W3138531978A5046454314 @default.
- W3138531978 hasAuthorship W3138531978A5073260424 @default.
- W3138531978 hasConcept C119857082 @default.
- W3138531978 hasConcept C120665830 @default.
- W3138531978 hasConcept C121332964 @default.
- W3138531978 hasConcept C123201435 @default.
- W3138531978 hasConcept C137822555 @default.
- W3138531978 hasConcept C142724271 @default.
- W3138531978 hasConcept C154945302 @default.
- W3138531978 hasConcept C192209626 @default.
- W3138531978 hasConcept C204787440 @default.
- W3138531978 hasConcept C2780385302 @default.
- W3138531978 hasConcept C2992525071 @default.
- W3138531978 hasConcept C38652104 @default.
- W3138531978 hasConcept C41008148 @default.
- W3138531978 hasConcept C71924100 @default.
- W3138531978 hasConcept C97541855 @default.
- W3138531978 hasConcept C99221444 @default.
- W3138531978 hasConceptScore W3138531978C119857082 @default.
- W3138531978 hasConceptScore W3138531978C120665830 @default.
- W3138531978 hasConceptScore W3138531978C121332964 @default.
- W3138531978 hasConceptScore W3138531978C123201435 @default.
- W3138531978 hasConceptScore W3138531978C137822555 @default.
- W3138531978 hasConceptScore W3138531978C142724271 @default.
- W3138531978 hasConceptScore W3138531978C154945302 @default.
- W3138531978 hasConceptScore W3138531978C192209626 @default.
- W3138531978 hasConceptScore W3138531978C204787440 @default.
- W3138531978 hasConceptScore W3138531978C2780385302 @default.
- W3138531978 hasConceptScore W3138531978C2992525071 @default.
- W3138531978 hasConceptScore W3138531978C38652104 @default.
- W3138531978 hasConceptScore W3138531978C41008148 @default.
- W3138531978 hasConceptScore W3138531978C71924100 @default.
- W3138531978 hasConceptScore W3138531978C97541855 @default.
- W3138531978 hasConceptScore W3138531978C99221444 @default.
- W3138531978 hasFunder F4320306076 @default.
- W3138531978 hasFunder F4320316514 @default.
- W3138531978 hasLocation W31385319781 @default.
- W3138531978 hasOpenAccess W3138531978 @default.
- W3138531978 hasPrimaryLocation W31385319781 @default.
- W3138531978 hasRelatedWork W118448456 @default.
- W3138531978 hasRelatedWork W2050283318 @default.
- W3138531978 hasRelatedWork W2172222246 @default.
- W3138531978 hasRelatedWork W2260680879 @default.
- W3138531978 hasRelatedWork W2290534421 @default.
- W3138531978 hasRelatedWork W2577220285 @default.
- W3138531978 hasRelatedWork W2596305496 @default.
- W3138531978 hasRelatedWork W2997789329 @default.
- W3138531978 hasRelatedWork W4309503015 @default.
- W3138531978 hasRelatedWork W58529046 @default.
- W3138531978 isParatext "false" @default.
- W3138531978 isRetracted "false" @default.
- W3138531978 magId "3138531978" @default.
- W3138531978 workType "article" @default.