Research map / Label-efficient and robust learning / OOD and anomaly detection
LOG: Active Model Adaptation for Label-Efficient OOD Generalization
Jie-Jing Shao, Lan-Zhe Guo, Xiao-wen Yang, Yu-Feng Li
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 |
|---|---|---|---|
| use both active query (MQ) and model adaptation (MA) instead of the better single-module variant (ablation) | LOG · Car insurance, 100 labels | overall error: .128 -> .123 | Improved |
| use both modules instead of the best single-module variant (ablation) | LOG · Income, 100 labels | overall error: .153 -> .150 | Improved |
| use both modules instead of the best single-module variant (ablation) | LOG · House, 100 labels | overall error: .296 -> .266 | Improved |
| use both modules instead of the best single-module variant (ablation) | LOG · Insurance, 100 labels | worst-case error: .168 -> .164 | Improved |
| use both modules instead of the best single-module variant (ablation) | LOG · Income, 100 labels | worst-case error: .277 -> .235 | Improved |
| use both modules instead of the best single-module variant (ablation) | LOG · House, 100 labels | worst-case error: .578 -> .439 | Improved |
| single-module variant row 2 on House (ablation) | LOG · House, 100 labels | overall error: .296 -> .344 | Hurt |
| random querying at larger label budgets | Random query · Income | worst-case error | Hurt |
| discrepancy-based querying (DBAL) early adaptation | DBAL · Income vs House | overall error | Mixed |
| active adaptation instead of source-only invariant methods HRM/EIIL | Active adaptation · synthetic shifts | overall error | Improved |
Closest papers by meaning
- Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization (ICLR 2023 · similarity 0.87)
- Towards Reliable Learning in the Wild: Generalization and Adaptation (AAAI 2024 · similarity 0.87)
- OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable? (ICML 2025 · similarity 0.86)
- Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization (NeurIPS 2024 · similarity 0.86)
- Robust Sampling for Active Statistical Inference (NeurIPS 2025 · similarity 0.86)
- Active Learning with LLMs for Partially Observed and Cost-Aware Scenarios (NeurIPS 2024 · similarity 0.85)
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.
