Research map / Learning theory and algorithms / Fairness
Achieving Fairness Without Harm via Selective Demographic Experts
Xuwei Tan, Yuanlong Wang, Thai-Hoang Pham, Ping Zhang, Xueru Zhang
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 |
|---|---|---|---|
| decouple only the classifiers (shared ERM representation) per sensitive group | ERM on Ham10000 · Ham10000 (gender) | AUC: 84.07 -> 83.60 | Hurt |
| decouple representations as well as classifiers with no-harm selection (FairSDE vs Decoupled) | Decoupled classifiers · Ham10000 (age) | AUC: 83.91 -> 84.62 | Improved |
| add FairSDE demographic experts with no-harm selection | ERM · Ham10000 (age) | worst-group AUC: 75.13 -> 76.03 | Improved |
| add FairSDE | ERM · UTKFace (race) | accuracy: 81.65 -> 84.17 | Improved |
| add FairSDE | ERM · MIMIC-CXR (gender) | AUC: 82.28 -> 82.60 | No clear effect |
| add FairSDE | ERM · Harvard-GF (gender) | AUC gap: 2.36 -> 1.81 | Improved |
| add FairSDE (no clear fairness gain on race gap vs ERM beyond small change) | ERM · Ham10000 (gender) | AUC gap: 2.76 -> 2.65 | No clear effect |
| use integer programming selection instead of greedy (ablation) | FairSDE on Harvard-GF (gender) · Harvard-GF (gender) | AUC gap: 2.34 -> 1.81 | Improved |
| use integer programming selection instead of greedy (ablation) | FairSDE on Harvard-GF (gender) · Harvard-GF (gender) | overall AUC: 82.31 -> 81.98 | Hurt |
| add fairness-regularization baseline FSCL+ | ERM · Ham10000 (gender) | AUC: 84.07 -> 82.18 | Hurt |
| add adversarial debiasing | ERM · UTKFace (gender) | accuracy: 78.06 -> 73.40 | Hurt |
| use greedy no-harm selection (ablation) | FairSDE · Harvard-GF (gender) | worst-group AUC: 80.54 -> 81.20 | Improved |
Closest papers by meaning
- FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis (ICLR 2024 · similarity 0.86)
- Rethinking Fair Representation Learning for Performance-Sensitive Tasks (ICLR 2025 · similarity 0.86)
- A Sequentially Fair Mechanism for Multiple Sensitive Attributes (AAAI 2024 · similarity 0.85)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.85)
- FairCLIP: Harnessing Fairness in Vision-Language Learning (CVPR 2024 · similarity 0.85)
- The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective (NeurIPS 2025 · similarity 0.84)
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.
