Research map / Learning theory and algorithms / Fairness
Why Is My Classifier Discriminatory?
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Increase training set size from 1000 to 10,000 samples | Adult income random forest · Adult income | FNR discrimination: decreases by a striking 40% | Helped |
| Increase training set size | Adult income random forest · Adult income | FPR and FNR | Helped |
| Increase training set size | MIMIC-III logistic regression · MIMIC-III mortality | group-specific prediction loss | Mixed |
| Increase training set size | Goodreads random forest · Goodreads ratings | MSE | Helped |
| Increase the female-to-male training-review ratio | Goodreads rating prediction · Goodreads ratings | MSE discrimination | Helped |
| Increase the number of features | Goodreads rating prediction · Goodreads ratings | MSE discrimination | No clear effect |
| Increase training data for cancer patients | MIMIC-III mortality prediction · MIMIC-III mortality, cancer patients | zero-one error | No clear effect |
| Use separate classifiers for each protected group instead of one population-wide classifier | The paper's prediction setup · Preliminary experiments | error rate | Hurt |
| Target additional sampling toward the less represented gender | Goodreads rating prediction · Goodreads ratings | MSE discrimination | Helped |
| Collect additional predictive features for cancer patients | MIMIC-III mortality prediction · MIMIC-III mortality, cancer patients | zero-one error | Mixed |
Closest papers by meaning
- On Fairness and Calibration (NeurIPS 2017 · similarity 0.89)
- Reconciling Predictive and Statistical Parity: A Causal Approach (AAAI 2024 · similarity 0.89)
- Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification (AAAI 2024 · similarity 0.87)
- Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis (NeurIPS 2025 · similarity 0.87)
- The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning (NeurIPS 2024 · similarity 0.87)
- Counterfactual Fairness by Combining Factual and Counterfactual Predictions (NeurIPS 2024 · 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.