AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Protecting the Protected Group: Circumventing Harmful Fairness

Omer Ben-Porat, Fedor Sandomirskiy, Moshe Tennenholtz

AAAI 2021 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Impose EO when its assumed utility is misaligned with the population's underlying utilityBank-optimal classifier · Constructed mismatch exampleA=1 underlying welfare: 1/3 -> 2/7Hurt
Use welfare-equalizing fairness when assumed and underlying utilities identify the same disadvantaged groupBank-optimal classifier · General theoremdisadvantaged-group underlying welfareImproved
Impose unawareness when the protected attribute changes how the observed feature predicts borrower qualityBank-optimal classifier · Constructed unawareness exampleboth groups' welfareHurt
Use an assumed utility that approximates the underlying utility closely enough for the unconstrained welfare gap to exceed the stated boundWelfare-equalizing fairness · General corollarydisadvantaged-group underlying welfareImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy