Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Adaptation meets Individual Fairness. And they get along.
Debarghya Mukherjee, Felix Petersen, Mikhail Yurochkin, Yuekai Sun
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 |
|---|---|---|---|
| apply SenSeI individual fairness regularizer | ERM baseline · Toxicity | TNR (annotations): 79.4% ± 2.2% -> 83.5% ± 1.7% | Improved |
| apply SenSeI individual fairness regularizer | ERM baseline · Bios | worst per-gender accuracy: 77.9% ± 0.4% -> 80.2% ± 0.4% | Improved |
| apply SenSeI individual fairness regularizer | ERM baseline · Toxicity | TNR (identity tokens): 75.0% ± 2.3% -> 79.4% ± 1.5% | Improved |
| apply SenSR | ERM baseline · Toxicity | TNR (annotations): 79.4% ± 2.2% -> 81.5% ± 1.1% | Improved |
| apply CLP counterfactual augmentation | ERM baseline · Bios | worst per-gender accuracy: 77.9% ± 0.4% -> 79.9% ± 0.3% | Improved |
| apply GLIF using unlabeled target samples | ERM baseline · Toxicity | balanced accuracy: 80.7% ± 0.2% -> 70.5% ± 7.1% | Hurt |
| apply GLIF using unlabeled target samples | ERM baseline · Toxicity | TNR (annotations): 79.4% ± 2.2% -> 87.0% ± 9.8% | Improved |
| apply GLIF | ERM baseline · Bios | worst per-gender accuracy: 77.9% ± 0.4% -> 77.6% ± 1.0% | No clear effect |
| apply WDA domain adaptation on fairness-motivated data split | ERM baseline · Toxicity | prediction consistency: 62.1% ± 1.4% -> 65.4% ± 1.3% | Improved |
| apply WDA domain adaptation on fairness-motivated data split | ERM baseline · Bios | prediction consistency: 94.2% ± 0.1% -> 95.5% ± 0.3% | Improved |
| apply WDA | ERM baseline · Bios | balanced accuracy: 84.2% ± 0.2% -> 83.3% ± 0.3% | Hurt |
| apply DANN | ERM baseline · Toxicity | prediction consistency: 62.1% ± 1.4% -> 62.8% ± 1.1% | No clear effect |
Closest papers by meaning
- Transferring Fairness under Distribution Shifts via Fair Consistency Regularization (NeurIPS 2022 · similarity 0.93)
- Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness (NeurIPS 2025 · similarity 0.88)
- Fairness without Demographics through Shared Latent Space-Based Debiasing (AAAI 2024 · similarity 0.87)
- AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data (CVPR 2025 · similarity 0.87)
- A Comprehensive View of Fairness through Distributional Stability (NeurIPS 2026 · similarity 0.87)
- Towards Harmless Rawlsian Fairness Regardless of Demographic Prior (NeurIPS 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.
