Research map / Learning theory and algorithms / Fairness
One-Network Adversarial Fairness
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 adversarial fairness layer (FAD, beta > 0) (ablation) | 2-layer neural network · COMPAS | DispDI: 0.6 -> 0.08 | Helped |
| add adversarial fairness layer (FAD, beta > 0) (ablation) | 2-layer neural network · Adult | DispDI: 0.71 -> 0.14 | Helped |
| add adversarial fairness layer (FAD, beta > 0) (ablation) | 2-layer neural network · COMPAS | accuracy: 89.3% -> 88.4% | Hurt |
| add adversarial fairness layer (FAD, beta > 0) (ablation) | 2-layer neural network · Adult | accuracy: 90.1% -> 88.6% | Hurt |
| add one-class SVM diverse minibatch selection (FAD-MD) (ablation) | FAD · COMPAS | accuracy: 88.4% -> 88.7% | Helped |
| add one-class SVM diverse minibatch selection (FAD-MD) (ablation) | FAD · Adult | accuracy: 88.6% -> 89% | Helped |
| add diverse minibatches (FAD-MD) (ablation) | FAD · COMPAS | DispDI: 0.08 -> 0.11 | Hurt |
| add diverse minibatches (FAD-MD) (ablation) | FAD · Adult | DispDI: 0.14 -> 0.13 | Helped |
| add diverse minibatches (FAD-MD) (ablation) | FAD · COMPAS and Adult | MMD test rejection rate | Helped |
| increase beta beyond 1 (ablation) | FAD · COMPAS and Adult | accuracy | No clear effect |
| use Salimans et al. minibatch heuristics (ablation) | FAD · COMPAS and Adult | accuracy | No clear effect |
Closest papers by meaning
- Adversarial Fairness Network (AAAI 2024 · similarity 0.91)
- On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness (ICML 2025 · similarity 0.89)
- On the Fairness ROAD: Robust Optimization for Adversarial Debiasing (ICLR 2024 · similarity 0.88)
- Fairness-Aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models (CVPR 2022 · similarity 0.88)
- Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces (AAAI 2024 · similarity 0.87)
- Adversarial Attacks on Fairness of Graph Neural Networks (ICLR 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.