AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Fair Performance Metric Elicitation

Gaurush Hiranandani, Harikrishna Narasimhan, Sanmi Koyejo

NeurIPS 2020 · Learning theory and algorithms › Fairness · approach: Fair allocation and selection

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
Elicit misclassification cost, fairness violation, and trade-off together with FPMERanking classifiers on default, adult, wine, and crime · Four real-world datasetsNDCGImproved
Elicit misclassification cost, fairness violation, and trade-off together with FPMERanking classifiers on default, adult, wine, and crime · Four real-world datasetsKendall-tauImproved
Elicit all three metric components instead of fixing one or more to defaults (ablation)FPME classifier ranking · Four real-world datasetsNDCGImproved
Use weighted rather than equally weighted default metric components (ablation)Baseline classifier ranking · Real-world datasets other than defaultNDCGImproved
Use weighted rather than equally weighted default metric components (ablation)Baseline classifier ranking · DefaultNDCGMixed
Recover the oracle metric using FPMERandomly generated oracle metrics · Synthetic elicitation experiments across k, m in {2,3,4,5}Metric recovery errorImproved

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