Research map / Label-efficient and robust learning / Domain adaptation and generalization
Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 domain-invariant check models as proxy labels to estimate target risk | Supervised and domain-invariant classifiers · SL-Digit | Err: 0.450 -> 0.073 | Helped |
| Use domain-invariant check models as proxy labels to estimate target risk | Supervised and domain-invariant classifiers · SL-Object | Err: 0.281 -> 0.034 | Helped |
| Use domain-invariant check models as proxy labels to estimate target risk | Supervised and domain-invariant classifiers · DIR-Digit | Err: 0.124 -> 0.043 | Helped |
| Use domain-invariant check models as proxy labels to estimate target risk | Supervised and domain-invariant classifiers · DIR-Object | Err: 0.114 -> 0.021 | Helped |
| Increase encoder depth beyond the optimal complexity (ablation) | DANN · MNIST→MNIST-M | target error: 19.8% | Hurt |
| Increase encoder depth beyond the optimal complexity (ablation) | DANN · SVHN→MNIST | target error: 8.8% | Hurt |
| Vary encoder width instead of encoder depth (ablation) | DANN · Digit classification | target error | No clear effect |
| Replace the CNN encoder with an MLP encoder (ablation) | DANN · MNIST→MNIST-M | target error | Hurt |
| Add 7 layers to the predictor (ablation) | DANN with encoder depth fixed · MNIST→MNIST-M | target error: 0.9% | Helped |
| Choose an optimal intermediate layer for the domain-invariant loss (ablation) | Fixed-depth DANN · MNIST→MNIST-M | target error: 19.5% | Mixed |
| Choose an optimal intermediate layer for the domain-invariant loss (ablation) | Fixed-depth DANN · SVHN→MNIST | target error: 10.4% | Mixed |
Closest papers by meaning
- Adaptive Risk Minimization: Learning to Adapt to Domain Shift (NeurIPS 2021 · similarity 0.91)
- Failure Modes of Domain Generalization Algorithms (CVPR 2022 · similarity 0.90)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.88)
- Domain-wise Data Acquisition to Improve Performance under Distribution Shift (ICML 2024 · similarity 0.88)
- Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains (AAAI 2024 · similarity 0.88)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · 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.