Research map / Learning theory and algorithms / Fairness
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie J Su, James Zou
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 |
|---|---|---|---|
| Add subgroup- and class-dependent FIFA logit margins | Grid Search with ResNet-18 · CelebA, ε=0.01 | Test fairness violation: 20.29% -> 2.75% | Improved |
| Add subgroup- and class-dependent FIFA logit margins | Grid Search with ResNet-18 · CelebA, ε=0.05 | Test combined loss: 13.05% -> 6.34% | Improved |
| Use FIFA margins instead of vanilla training | Logistic regression with Exponentiated Gradient · AdultIncome, ε=0.01 | Test fairness violation: 6.7475% -> 2.7776% | Improved |
| Use FIFA margins instead of vanilla training | Logistic regression with Exponentiated Gradient · DutchConsensus, ε=0.05 | Test fairness violation: 4.4323% -> 4.4323% | No clear effect |
| Add logits-based LDAM margins (α=0 and all δ=0) (ablation) | Grid Search with ResNet-18 · CelebA, ε=0.01 | Test combined loss: 14.01% -> 7.29% | Improved |
| Tune subgroup fairness margins and α beyond LDAM (ablation) | LDAM / FIFA loss with Grid Search · CelebA, ε=0.01 | Test fairness violation: 5.39% -> 2.75% | Improved |
| Add FIFA margins instead of vanilla loss | Grid Search with ResNet-18 · CelebA, ε=0.10 | Test combined loss: 16.71% -> 6.54% | Improved |
Closest papers by meaning
- Fair Domain Generalization: An Information-Theoretic View (AAAI 2026 · similarity 0.88)
- Fairness via Independence: A General Regularization Framework for Machine Learning (ICLR 2026 · similarity 0.88)
- Individual Fairness In Strategic Classification (NeurIPS 2025 · similarity 0.86)
- Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning (NeurIPS 2025 · similarity 0.86)
- Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective (ICML 2025 · similarity 0.86)
- FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation (ICML 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.
