Research map / Label-efficient and robust learning / Semi-supervised learning
Resilient Semi-Supervised Inference with Heterogeneous Unlabeled Data
Mengyuan Wang, Chengde Qian, Haojie Ren, Changliang Zou
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a semi-supervised inference method robust to distribution shift between labeled and heterogeneous unlabeled data, building on model-assisted (prediction-powered) estimation.
Problem
Model-assisted semi-supervised inference (e.g., prediction-powered inference) assumes labeled and unlabeled populations share the same distribution, which can fail when unlabeled data are heterogeneous.
Approach
Makes semi-supervised estimation resilient to heterogeneity in the unlabeled data, so validity does not require identical labeled and unlabeled distributions; the abstract is truncated so the exact mechanism is not stated.
Limitations
- Abstract is truncated; full method and results not available
Experimental setup
Baselines: prediction-powered inference
Builds on: prediction-powered inference
Closest papers by meaning
- Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data (AAAI 2024 · similarity 0.88)
- Prediction-Powered Semi-Supervised Learning with Online Power Tuning (NeurIPS 2025 · similarity 0.88)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.88)
- A Unified Framework for Heterogeneous Semi-supervised Learning (CVPR 2025 · similarity 0.88)
- Out-Of-Domain Unlabeled Data Improves Generalization (ICLR 2024 · similarity 0.87)
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels (NeurIPS 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.
