Research map / Label-efficient and robust learning / Domain adaptation and generalization
A Theory of Label Propagation for Subpopulation Shift
Tianle Cai, Ruiqi Gao, Jason Lee, Qi Lei
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 |
|---|---|---|---|
| Replace distribution matching (MDD) with consistency-based FixMatch label propagation on ENTITY-30 subpopulation shift | SwAV-finetuned ResNet50 on ENTITY-30 · ENTITY-30 UDA target | Target Acc: +8.65 over MDD (72.60 vs 63.95) | Improved |
| Add FixMatch consistency-based adaptation on top of source-only training | SwAV-finetuned ResNet50 on ENTITY-30 · ENTITY-30 UDA target | Target Acc: +15.87 over source-only (72.60 vs 56.73) | Improved |
| Add FixMatch finetuning on top of MDD on Office-31 | MDD · Office-31 (6 transfer tasks) | average accuracy: +0.68 (89.84 vs 89.16) | Improved |
| Add FixMatch finetuning on top of MDD on Office-Home | MDD · Office-Home (12 transfer tasks) | average accuracy: +1.6 (69.6 vs 68.0) | Improved |
| Add FixMatch on top of source-trained model: source accuracy under FixMatch decreases slightly | FixMatch on ENTITY-30 · ENTITY-30 UDA source | Source Acc: -1.04 vs source-only (90.87 vs 91.91) | Hurt |
| Add DANN domain-adversarial training on ENTITY-30 | SwAV-finetuned ResNet50 · ENTITY-30 UDA target | Target Acc: +4.3 over source-only (61.03 vs 56.73), with high variance (±4.63) | Improved |
| Add MDD distribution matching on ENTITY-30 | SwAV-finetuned ResNet50 · ENTITY-30 UDA target | Target Acc: +7.22 over source-only (63.95 vs 56.73) | Improved |
Closest papers by meaning
- Efficient Inference under Label Shift in Unsupervised Domain Adaptation (JMLR 2026 · similarity 0.90)
- Regularized Learning for Domain Adaptation under Label Shifts (ICLR 2019 · similarity 0.88)
- Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift (NeurIPS 2020 · similarity 0.88)
- ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models (ICML 2023 · similarity 0.88)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.87)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · 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.
