Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation
Check 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 |
|---|---|---|---|
| jointly align marginal feature distributions and conditional label distributions | LIRR · image classification and WebCamT traffic counting | accuracy or MAE | Helped |
| add a cosine classifier to LIRR (ablation) | LIRR · image classification benchmarks | accuracy: 86.80 -> 89.67; 84.78 -> 89.73 | Helped |
| optimize invariant representations and invariant risks together rather than only one objective (ablation) | Semi-DA · classification and regression tasks | accuracy or MAE | Helped |
| set lambda_rep to 0.01 and lambda_risk to 0.1 (ablation) | LIRR · OfficeHome Art to Real | accuracy: 70.23 -> 73.12 | Helped |
| increase the proportion of labeled target data (ablation) | LIRR · Semi-DA classification | accuracy | Helped |
Closest papers by meaning
- Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? (NeurIPS 2021 · similarity 0.91)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.89)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.89)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.88)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.88)
- Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling (AAAI 2024 · similarity 0.88)
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.