Research map / Learning theory and algorithms / Fairness
FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret
Vishnu Suresh Lokhande, Aditya Kumar Akash, Sathya N. Ravi, Vikas Singh
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| replace Quadrianto et al. with FairALM constraint | FairALM · CelebA (attractiveness, protected gender) | DEO (%): 12.4 -> 10.4 | Improved |
| replace Fairness GAN with FairALM | FairALM · CelebA (attractiveness, protected gender) | DEO (%): 22.5 -> 10.4 | Improved |
| add FairALM fairness constraint to 3-layer ReLU net | 3-layer ReLU net · CelebA (40 labels) | precision: +-5% | No clear effect |
| use FairALM instead of naive l2 penalty | ResNet-18 · CelebA (attractiveness) | training stability | Improved |
| add FairALM to unconstrained model | ResNet-18 · ImSitu (Shaving vs Moisturize) | DEO (%): 4.2 -> 0.0 | Improved |
| add FairALM to unconstrained model | ResNet-18 · ImSitu (Cooking vs Driving) | DEO (%): 7.1 -> 0.0 | Improved |
| add FairALM to unconstrained model | ResNet-18 · ImSitu (Washing vs Saluting) | DEO (%): 25.9 -> 0.0 | Improved |
| add FairALM to unconstrained model | ResNet-18 · ImSitu (Assembling vs Hanging) | DEO (%): 15.0 -> 0.0 | Improved |
| use FairALM instead of Lagrangian | ResNet-18 · ImSitu (Shaving vs Moisturize) | test error (ERR, %): 12.4 -> 20.0 | Hurt |
| use FairALM instead of Proxy-Lagrangian | ResNet-18 · ImSitu (Assembling vs Hanging) | DEO (%): 26.0 -> 0.0 | Improved |
| use FairALM for dataset pooling (site as protected variable) | ResNet-18 · Chest X-ray TB (Shenzhen + Montgomery) | test error variance | Improved |
| use FairALM instead of Agarwal et al. | logistic regression · Adult | DEO (%): 1.0 -> 0.7 ± 0.6 | Improved |
Closest papers by meaning
- On the Fairness ROAD: Robust Optimization for Adversarial Debiasing (ICLR 2024 · similarity 0.89)
- Classes Are Not Equal: An Empirical Study on Image Recognition Fairness (CVPR 2024 · similarity 0.88)
- FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation (ICML 2025 · similarity 0.88)
- Leveraging Diffusion Perturbations for Measuring Fairness in Computer Vision (AAAI 2024 · similarity 0.87)
- FairCLIP: Harnessing Fairness in Vision-Language Learning (CVPR 2024 · similarity 0.87)
- DAFA: Distance-Aware Fair Adversarial Training (ICLR 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.
