Research map / Learning theory and algorithms / Fairness
Fair and Accurate Decision Making through Group-Aware Learning
Ramtin Hosseini, Li Zhang, Bhanu Garg, Pengtao Xie
AI-extracted. The measured effects below were read by AI from the paper's full text (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 Learning by Grouping (LBG) | ResNet18 · CelebA | DEO: 0.5683 -> 0.0596 | Improved |
| add LBG | DARTS · CelebA | error (%): 16.39 -> 15.91 | Improved |
| add domain adaptation (DALBG) on top of LBG | LBG-DARTS · CelebA | error (%): 15.91 -> 15.22 | Improved |
| add domain adaptation (DALBG) on top of LBG | LBG-ResNet18 · CelebA | DEO: 0.0596 -> 0.0835 | Hurt |
| add LBG | ResNet18 · ISIC-18 | error (%): 14.3 -> 12.8 | Improved |
| add LBG | DARTS · ISIC-18 | SPD: 0.121 -> 0.048 | Improved |
| add DALBG to ResNet56 instead of vanilla | ResNet56 · CIFAR-100 | test error (%): 31.46 -> 27.95 | Improved |
| apply DALBG to Swin-T | Swin-T · ImageNet | test error (%): 18.70 -> 16.64 | Improved |
| apply DALBG to DARTS | DARTS · CIFAR-100 | test error (%): 20.58 -> 17.97 | Improved |
| apply LBG to PC-DARTS | PC-DARTS · CIFAR-100 | test error (%): 17.96 -> 16.21 | Improved |
| apply DALBG to PC-DARTS | PC-DARTS · ImageNet | top-1 error (%): 24.8 -> 23.1 | Improved |
| increase tradeoff lambda 0 -> 0.1 -> 1 (ablation) | DALBG-DARTS · CelebA | error (%): 15.91 -> 15.22 -> 15.38 | Mixed |
Closest papers by meaning
- Providing Fair Recourse over Plausible Groups (AAAI 2024 · similarity 0.87)
- Enhancing Group Fairness in Online Settings Using Oblique Decision Forests (ICLR 2024 · similarity 0.86)
- Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness (NeurIPS 2025 · similarity 0.86)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.86)
- Fairness-Aware Meta-Learning via Nash Bargaining (NeurIPS 2024 · similarity 0.86)
- Metric-Agnostic Continual Learning for Sustainable Group Fairness (AAAI 2025 · 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.
