Research map / Label-efficient and robust learning / Domain adaptation and generalization
On Causality in Domain Adaptation and Semi-Supervised Learning: an Information-Theoretic Analysis for Parametric Models
Xuetong Wu, Mingming Gong, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| add unlabelled target data in causal learning under general shift | MLE parametric model, toy example · Toy causal learning, general shift | excess risk: risk will remain around 0.34 | No clear effect |
| add unlabelled target data (up to 1,000) in anti-causal GMM learning | GMM with EM · MNIST digit pair (2,5), 100 labelled samples | accuracy: approximately 99% accuracy when the data size exceeds 500 | Improved |
| add labelled source data in anti-causal target shift or conditional shift | MLE parametric model, toy example · Toy anti-causal learning | excess risk | Mixed |
Closest papers by meaning
- Anti-causal domain generalization: Leveraging unlabeled data (ICML 2026 · similarity 0.90)
- Domain adaptation under structural causal models (JMLR 2021 · similarity 0.89)
- Transporting Causal Mechanisms for Unsupervised Domain Adaptation (ICCV 2021 · similarity 0.89)
- Causality Inspired Representation Learning for Domain Generalization (CVPR 2022 · similarity 0.89)
- Do causal predictors generalize better to new domains? (NeurIPS 2024 · similarity 0.89)
- Sparse Causal Discovery with Generative Intervention for Unsupervised Graph 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.
