Research map / Label-efficient and robust learning / Domain adaptation and generalization
RLSbench: Domain Adaptation Under Relaxed Label Shift
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 |
|---|---|---|---|
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to DANN (ablation) | DANN · Civilcomments | accuracy: 86.6 -> 88.8 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to CDANN (ablation) | CDANN · Civilcomments | accuracy: 86.9 -> 88.9 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to PseudoLabel (ablation) | PseudoLabel · Civilcomments | accuracy: 87.4 -> 88.6 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to DANN (ablation) | DANN · Retiring Adults | accuracy: 77.2 -> 79.4 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to CDANN (ablation) | CDANN · Retiring Adults | accuracy: 78.1 -> 80.4 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to PseudoLabel (ablation) | PseudoLabel · Retiring Adults | accuracy: 78.3 -> 80.8 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to DANN (ablation) | DANN · Mimic Readmission | accuracy: 56.4 -> 59.2 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to CDANN (ablation) | CDANN · Mimic Readmission | accuracy: 56.7 -> 59.9 | Helped |
| Apply pseudo-balancing (RS) and post-hoc reweighting (RW) to PseudoLabel (ablation) | PseudoLabel · Mimic Readmission | accuracy: 57.4 -> 57.9 | No clear effect |
| Use pseudo-balancing (RS) as target label-marginal shift grows (ablation) | DA methods across RLSbench · RLSbench | accuracy | Helped |
| Use pseudo-balancing (RS) with absent or very small label-marginal shift (ablation) | DA methods across RLSbench · RLSbench | accuracy: <0.5% | No clear effect |
| Use post-hoc reweighting (RW) under severe label-marginal shift (ablation) | DANN, CDANN, FixMatch, and PseudoLabel · RLSbench | accuracy | Helped |
Closest papers by meaning
- Domain Adaptation under Open Set Label Shift (NeurIPS 2022 · similarity 0.93)
- Regularized Learning for Domain Adaptation under Label Shifts (ICLR 2019 · similarity 0.92)
- ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models (ICML 2023 · similarity 0.91)
- Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments (AAAI 2024 · similarity 0.88)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · similarity 0.88)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · 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.