Research map / Learning theory and algorithms / Fairness
Fairness and Explainability: Bridging the Gap towards Fair Model Explanations
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 |
|---|---|---|---|
| Apply CFA instead of the strongest listed baseline | fair classification · Recidivism | Score: 76.19±0.00 -> 82.33±0.62 | Helped |
| Apply CFA instead of the strongest listed baseline | fair classification · German | Score: 41.18±0.00 -> 53.34±7.27 | Helped |
| Apply CFA instead of the strongest listed baseline | fair classification · Por | Score: 57.60±0.00 -> 61.55±3.26 | Helped |
| Apply CFA instead of the strongest listed baseline | fair classification · Math | Score: 72.79±3.76 -> 81.12±5.59 | Helped |
| Use Sliced-Wasserstein distance in the fairness objective (ablation) | CFA · Recidivism | Score: 82.17±0.93 | Helped |
| Use negative cosine similarity in the fairness objective (ablation) | CFA · Recidivism | Score: 82.71±4.01 | Helped |
| Use KL divergence in the fairness objective (ablation) | CFA · Recidivism | Score: 78.44±4.81 | Helped |
| Use mean square error in the fairness objective (ablation) | CFA · Recidivism | Score: 80.36±1.61 | Helped |
| Increase the fairness regularization coefficient λ | CFA · Por | fairness performance | Helped |
| Increase the fairness regularization coefficient λ | CFA · Por | utility performance | Hurt |
| Add explanation-fairness optimization | NIFTY and FairVGNN · graph domain | traditional and explanation fairness | Helped |
| Add explanation-fairness optimization | NIFTY · graph domain | utility performance | Hurt |
Closest papers by meaning
- Constructing Fair Latent Space for Intersection of Fairness and Explainability (AAAI 2025 · similarity 0.90)
- Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making (NeurIPS 2024 · similarity 0.88)
- The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning (NeurIPS 2024 · similarity 0.87)
- Reconciling Predictive and Statistical Parity: A Causal Approach (AAAI 2024 · similarity 0.87)
- Generating Diagnostic and Actionable Explanations for Fair Graph Neural Networks (AAAI 2024 · similarity 0.87)
- Identifying Reasons for Bias: An Argumentation-Based Approach (AAAI 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.