Research map / Learning theory and algorithms / Fairness
Individually Fair Rankings
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 |
|---|---|---|---|
| Add the SenSTIR optimal-transport individual-fairness regularizer | Linear learning-to-rank models · Synthetic ranking task | Individual fairness | Helped |
| Increase SenSTIR fairness regularization strength ρ (ablation) | SenSTIR · Synthetic ranking task | Ranking stability under sensitive perturbations | Helped |
| Use Fair-PG-Rank instead of SenSTIR | Linear learning-to-rank models · Synthetic ranking task | Ranking stability under sensitive perturbations | Hurt |
| Add the SenSTIR fairness regularizer | Linear learning-to-rank models · German Credit | Kendall's tau | Helped |
| Increase SenSTIR regularization strength ρ (ablation) | SenSTIR · German Credit | NDCG | Mixed |
| Project features onto the orthogonal complement of the sensitive subspace before vanilla training | Project baseline · German Credit | Kendall's tau | Hurt |
| Use individual-fairness regularization rather than group-exposure regularization | SenSTIR versus Fair-PG-Rank · German Credit | Group exposure disparity | Helped |
| Add the SenSTIR fairness regularizer | Linear learning-to-rank models · Microsoft Learning to Rank | Kendall's tau | Helped |
| Increase Fair-PG-Rank regularization strength (ablation) | Fair-PG-Rank · Microsoft Learning to Rank | NDCG | Hurt |
| Increase Fair-PG-Rank regularization strength (ablation) | Fair-PG-Rank · Microsoft Learning to Rank | Group exposure disparity | Hurt |
| Increase SenSTIR regularization strength ρ (ablation) | SenSTIR · Microsoft Learning to Rank | NDCG | Mixed |
Closest papers by meaning
- Policy Learning for Fairness in Ranking (NeurIPS 2019 · similarity 0.90)
- Stability and Multigroup Fairness in Ranking with Uncertain Predictions (ICML 2024 · similarity 0.87)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.87)
- Individual Fairness In Strategic Classification (NeurIPS 2025 · similarity 0.86)
- Towards Harmless Rawlsian Fairness Regardless of Demographic Prior (NeurIPS 2024 · similarity 0.86)
- Fairness without Demographics through Shared Latent Space-Based Debiasing (AAAI 2024 · similarity 0.86)
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.