Differential Fairness

Simple item page
dc.contributor.authorFoulds, James R.
dc.contributor.authorIslam, Rashidul
dc.contributor.authorKeya, Kamrun Naher
dc.contributor.authorPan, Shimei
dc.date.accessioned2020-02-06T16:17:02Z
dc.date.available2020-02-06T16:17:02Z
dc.date.issued2019
dc.descriptionNeurIPS 2019 Workshop on Machine Learning with Guarantees, Vancouver, Canada.en_US
dc.description.abstractWe propose differential fairness, a multi-attribute definition of fairness in machine learning which is informed by the framework of intersectionality, a critical lens arising from the humanities literature, leveraging connections between differential privacy and legal notions of fairness. We show that our criterion behaves sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our differential fairness criterion. Experiments on the COMPAS criminal recidivism dataset and census data demonstrate the utility of our methods.en_US
dc.description.urihttp://jfoulds.informationsystems.umbc.edu/papers/2019/Foulds%20(2019)%20-%20DifferentialFairness_NeurIPS_MLWG.pdfen_US
dc.format.extent16 pagesen_US
dc.genrepresentations (communicative events)en_US
dc.identifierdoi:10.13016/m2ks4s-t0iv
dc.identifier.citationFoulds, James R.; Islam, Rashidul; Keya, Kamrun Naher; Pan, Shimei; Differential Fairness; NeurIPS 2019 Workshop on Machine Learning with Guarantees, Vancouver, Canada. (2019); https://www.semanticscholar.org/paper/Differential-Fairness-Foulds-Islam/cf3081d5fa83750a89898ae1adcef7925ed8af81en_US
dc.identifier.urihttp://hdl.handle.net/11603/17222
dc.language.isoen_USen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Information Systems Department Collection
dc.relation.ispartofUMBC Student Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.titleDifferential Fairnessen_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
81d5fa83750a89898ae1adcef7925ed8af81.pdf
Size:
924.39 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Information Systems Department
UMBC Faculty Collection
UMBC Student Collection