Research map / Learning theory and algorithms / Fairness
Average Individual Fairness: Algorithms, Generalization and Experiments
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 |
|---|---|---|---|
| use AIF-Learn instead of mixtures of the error-optimal classifier and random classification | Communities and Crime · Communities and Crime | error and individual error variation | Helped |
| decrease the allowed fairness violation parameter α | AIF-Learn · Communities and Crime | individual error variation | Helped |
| decrease the allowed fairness violation parameter α | AIF-Learn · Communities and Crime | overall error | Hurt |
| evaluate the learned mapping on held-out individuals and problems instead of training data | AIF-Learn · Communities and Crime holdout | error and fairness violation | Mixed |
Closest papers by meaning
- Individual Fairness In Strategic Classification (NeurIPS 2025 · similarity 0.90)
- Monotone Individual Fairness (ICML 2024 · similarity 0.90)
- Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility (NeurIPS 2026 · similarity 0.89)
- Reconciling Predictive and Statistical Parity: A Causal Approach (AAAI 2024 · similarity 0.88)
- Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification (AAAI 2024 · similarity 0.88)
- Identifying Reasons for Bias: An Argumentation-Based Approach (AAAI 2024 · similarity 0.88)
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.