AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Faking Fairness via Stealthily Biased Sampling

Kazuto Fukuchi, Satoshi Hara, Takanori Maehara

AAAI 2020 · Learning theory and algorithms › Fairness · approach: Causal and policy fairness in decisions · 19 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
Use stealthily biased sampling instead of random sampling to construct the disclosed benchmarkDecision-maker's benchmark dataset · Synthetic loan checkdemographic parity: 0.2 -> less than 0.1Improved
Use case-control sampling instead of stealthily biased samplingDecision-maker's benchmark dataset · Synthetic loan checkdemographic parityNo clear effect
Preserve similarity to the original feature distribution while enforcing fairnessStealthily biased sampling · Synthetic loan checkKS-test rejection rate: around 0.05Improved
Use stealthily biased sampling rather than case-control samplingDecision-maker's benchmark dataset · Synthetic loan checkKS-test rejection rateImproved
Use stealthily biased sampling rather than case-control samplingDecision-maker's benchmark dataset · COMPASWasserstein distanceImproved
Use stealthily biased sampling to select the disclosed subsetCOMPAS risk-score decisions · COMPASdemographic parityImproved
Use stealthily biased sampling to select the disclosed subsetLogistic-regression decisions · Adultdemographic parityImproved
Use stealthily biased sampling with stochastic rather than deterministic decisionsSynthetic loan check decision-maker · Synthetic loan checkrange of positive-decision ratios that evade detection: α=0.6 -> α between 0.25 and 0.95Improved

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