Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved

Published: Nov 27, 2018
Abstract
Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Probabilistic models for predicting the protected class based on observable proxies, such as surname and geolocation for race, are sometimes used to impute these missing labels for compliance assessments. Empirically, these methods are observed to exaggerate disparities, but...
Paper Details
Title
Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
Published Date
Nov 27, 2018
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.