Research map / Learning theory and algorithms / Fairness
Individual Arbitrariness and Group Fairness
Carol Xuan Long, Hsiang Hsu, Wael Alghamdi, Flavio Calmon
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 changed | Where | Measured | Effect |
|---|---|---|---|
| apply group fairness intervention (REDUCTION) | baseline random forest · ENEM | Mean EO violation: 0.28 -> 0.04 | Improved |
| apply group fairness intervention (REDUCTION) | baseline random forest · ENEM | accuracy: 67% -> 66% | Hurt |
| apply fairness interventions REDUCTION, ROC | baseline random forest · ENEM | per-sample score std. across seeds (top 50% of samples) | Hurt |
| apply fairness interventions REDUCTION, ROC | baseline random forest · ENEM | per-sample score std. across seeds (bottom 50% of samples) | Improved |
| apply fairness interventions to random forest baseline | random forest · ENEM, HSLS, Adult | maximal score std. at top quantiles: 0.5 | Hurt |
| use LEVERAGING intervention | baseline GBM and logistic regression · ENEM, HSLS, Adult | score arbitrariness | No clear effect |
| use LEVERAGING intervention | random forest · ENEM | agreement across seeds: 90% | No clear effect |
| vary fairness level (high vs low fairness constraint) in REDUCTION | random forest · ENEM, HSLS | score std. | No clear effect |
| threshold baseline scores | baseline classifier · student performance | score std.: 0.15 | Mixed |
| increase ensemble size m from 1 to 30 (uniform ensembling) | REDUCTION fair random forest models · ENEM | top-percentile score std.: m = 30 | Improved |
| increase ensemble size m (uniform ensembling) | REDUCTION fair random forest models · HSLS | top-percentile score std.: m = 17 | Improved |
| ensemble fair models | REDUCTION fair random forest models · ENEM | Mean EO violation: 0.06 | No clear effect |
Closest papers by meaning
- Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification (AAAI 2024 · similarity 0.89)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.88)
- Individual Fairness In Strategic Classification (NeurIPS 2025 · similarity 0.88)
- Multiaccuracy and Multicalibration via Proxy Groups (ICML 2025 · similarity 0.87)
- Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness (NeurIPS 2025 · similarity 0.87)
- Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis (NeurIPS 2025 · similarity 0.87)
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.
