Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999167212> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2999167212 abstract "Machine learning is increasingly becoming a powerful tool to make decisions in a wide variety of applications, such as medical diagnosis and autonomous driving. Privacy concerns related to the training data and unfair behaviors of some decisions with regard to certain attributes (e.g., sex, race) are becoming more critical. Thus, constructing a fair machine learning model while simultaneously providing privacy protection becomes a challenging problem. In this paper, we focus on the design of classification model with fairness and differential privacy guarantees by jointly combining functional mechanism and decision boundary fairness. In order to enforce $epsilon$-differential privacy and fairness, we leverage the functional mechanism to add different amounts of Laplace noise regarding different attributes to the polynomial coefficients of the objective function in consideration of fairness constraint. We further propose an utility-enhancement scheme, called relaxed functional mechanism by adding Gaussian noise instead of Laplace noise, hence achieving $(epsilon,delta)$-differential privacy. Based on the relaxed functional mechanism, we can design $(epsilon,delta)$-differentially private and fair classification model. Moreover, our theoretical analysis and empirical results demonstrate that our two approaches achieve both fairness and differential privacy while preserving good utility and outperform the state-of-the-art algorithms." @default.
- W2999167212 created "2020-01-23" @default.
- W2999167212 creator A5001877853 @default.
- W2999167212 creator A5006252544 @default.
- W2999167212 creator A5024569123 @default.
- W2999167212 creator A5029406631 @default.
- W2999167212 creator A5047722991 @default.
- W2999167212 creator A5050670610 @default.
- W2999167212 date "2020-01-14" @default.
- W2999167212 modified "2023-10-16" @default.
- W2999167212 title "Differentially Private and Fair Classification via Calibrated Functional Mechanism" @default.
- W2999167212 cites W1557833142 @default.
- W2999167212 cites W1873763122 @default.
- W2999167212 cites W2014352947 @default.
- W2999167212 cites W2026019770 @default.
- W2999167212 cites W2027595342 @default.
- W2999167212 cites W2040825624 @default.
- W2999167212 cites W2051267297 @default.
- W2999167212 cites W2052138360 @default.
- W2999167212 cites W2097415784 @default.
- W2999167212 cites W2100960835 @default.
- W2999167212 cites W2110921501 @default.
- W2999167212 cites W2162379889 @default.
- W2999167212 cites W2282546112 @default.
- W2999167212 cites W2530395818 @default.
- W2999167212 cites W2540757487 @default.
- W2999167212 cites W2785487418 @default.
- W2999167212 cites W2946346162 @default.
- W2999167212 cites W2948129334 @default.
- W2999167212 cites W2963559079 @default.
- W2999167212 cites W3023309920 @default.
- W2999167212 cites W3120740533 @default.
- W2999167212 doi "https://doi.org/10.48550/arxiv.2001.04958" @default.
- W2999167212 hasPublicationYear "2020" @default.
- W2999167212 type Work @default.
- W2999167212 sameAs 2999167212 @default.
- W2999167212 citedByCount "0" @default.
- W2999167212 crossrefType "posted-content" @default.
- W2999167212 hasAuthorship W2999167212A5001877853 @default.
- W2999167212 hasAuthorship W2999167212A5006252544 @default.
- W2999167212 hasAuthorship W2999167212A5024569123 @default.
- W2999167212 hasAuthorship W2999167212A5029406631 @default.
- W2999167212 hasAuthorship W2999167212A5047722991 @default.
- W2999167212 hasAuthorship W2999167212A5050670610 @default.
- W2999167212 hasBestOaLocation W29991672121 @default.
- W2999167212 hasConcept C115961682 @default.
- W2999167212 hasConcept C119857082 @default.
- W2999167212 hasConcept C124101348 @default.
- W2999167212 hasConcept C153083717 @default.
- W2999167212 hasConcept C154945302 @default.
- W2999167212 hasConcept C23130292 @default.
- W2999167212 hasConcept C38652104 @default.
- W2999167212 hasConcept C41008148 @default.
- W2999167212 hasConcept C99221444 @default.
- W2999167212 hasConcept C99498987 @default.
- W2999167212 hasConceptScore W2999167212C115961682 @default.
- W2999167212 hasConceptScore W2999167212C119857082 @default.
- W2999167212 hasConceptScore W2999167212C124101348 @default.
- W2999167212 hasConceptScore W2999167212C153083717 @default.
- W2999167212 hasConceptScore W2999167212C154945302 @default.
- W2999167212 hasConceptScore W2999167212C23130292 @default.
- W2999167212 hasConceptScore W2999167212C38652104 @default.
- W2999167212 hasConceptScore W2999167212C41008148 @default.
- W2999167212 hasConceptScore W2999167212C99221444 @default.
- W2999167212 hasConceptScore W2999167212C99498987 @default.
- W2999167212 hasLocation W29991672121 @default.
- W2999167212 hasOpenAccess W2999167212 @default.
- W2999167212 hasPrimaryLocation W29991672121 @default.
- W2999167212 hasRelatedWork W2963281172 @default.
- W2999167212 hasRelatedWork W2966023840 @default.
- W2999167212 hasRelatedWork W2966972880 @default.
- W2999167212 hasRelatedWork W3174280055 @default.
- W2999167212 hasRelatedWork W3200879895 @default.
- W2999167212 hasRelatedWork W4221159213 @default.
- W2999167212 hasRelatedWork W4286905691 @default.
- W2999167212 hasRelatedWork W4288054996 @default.
- W2999167212 hasRelatedWork W4293522974 @default.
- W2999167212 hasRelatedWork W4312795512 @default.
- W2999167212 isParatext "false" @default.
- W2999167212 isRetracted "false" @default.
- W2999167212 magId "2999167212" @default.
- W2999167212 workType "article" @default.