Research map / Label-efficient and robust learning / Domain adaptation and generalization
Few-shot Domain Adaptation by Causal Mechanism Transfer
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 |
|---|---|---|---|
| Transfer using the shared-mechanism estimate and target-IC recombination rather than TarOnly | Mechanism transfer · Gasoline consumption, 18 country targets | normalized MSE | Mixed |
| Transfer using the shared-mechanism estimate and target-IC recombination rather than TarOnly | Mechanism transfer · Gasoline consumption; DEU target | normalized MSE: 16.99 (8.04) -> 6.71 (1.23) | Helped |
| Transfer using the shared-mechanism estimate and target-IC recombination rather than TarOnly | Mechanism transfer · Gasoline consumption; GBR target | normalized MSE: 5.95 (1.86) -> 2.66 (0.57) | Helped |
| Transfer using the shared-mechanism estimate and target-IC recombination rather than TarOnly | Mechanism transfer · Gasoline consumption; USA target | normalized MSE: 4.98 (1.96) -> 1.60 (0.42) | Helped |
| Use mechanism transfer rather than TarOnly | Mechanism transfer · Gasoline consumption; IRL target | normalized MSE: 3.05 (0.34) -> 4.35 (1.25) | Hurt |
| Use mechanism transfer rather than TarOnly | Mechanism transfer · Gasoline consumption; ITA target | normalized MSE: 13.00 (4.15) -> 14.05 (4.81) | Hurt |
| Use mechanism transfer rather than the strongest naive baseline | Mechanism transfer · Gasoline consumption; NLD target | normalized MSE: 0.99 (0.06) -> 3.87 (0.79) | Hurt |
Closest papers by meaning
- Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions (NeurIPS 2018 · similarity 0.91)
- Domain Adaptation with Conditional Transferable Components (ICML 2016 · similarity 0.89)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 2025 · similarity 0.87)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.86)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.86)
- Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation (ICML 2025 · similarity 0.86)
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.