Research map / Label-efficient and robust learning / Recognition and long-tail
Adapting to Shifting Correlations with Unlabeled Data Calibration
Minh Nguyen, Alan Q Wang, Heejong Kim, Mert Sabuncu
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 |
|---|---|---|---|
| withhold confounders Z at test time and marginalize with input knockout (ablation) | GPA · Color MNIST | F1: decrease of 1-2% | Hurt |
| replace direct prevalence estimation from labels (CoPA) with EM estimation from unlabeled data (GPA) | CoPA · Color MNIST | F1 | Hurt |
| replace CoPA with GPA (EM-based prevalence estimation) | CoPA · ISIC and CXR | F1 | Improved |
| use domain adaptation (CoPA or GPA) instead of ERM | ERM · Color MNIST | F1 | Improved |
| marginalize over Z with input knockout instead of using Z at adaptation (ablation) | GPA · ISIC and CXR | F1 | No clear effect |
Closest papers by meaning
- CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts (NeurIPS 2024 · similarity 0.84)
- Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables (NeurIPS 2024 · similarity 0.84)
- Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift (NeurIPS 2024 · similarity 0.84)
- Mitigating Spurious Correlations via Disagreement Probability (NeurIPS 2024 · similarity 0.83)
- Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line (NeurIPS 2024 · similarity 0.83)
- Fairness under Covariate Shift: Improving Fairness-Accuracy Tradeoff with Few Unlabeled Test Samples (AAAI 2024 · similarity 0.83)
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.
