Research map / Label-efficient and robust learning / Recognition and long-tail
Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning
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 |
|---|---|---|---|
| Use PU learning instead of PN learning when π/√n_+ + 1/√n_u < (1-π)/√n_- | PN learning · Finite-sample theoretical comparison | estimation error bound | Helped |
| Use NU learning instead of PN learning when (1-π)/√n_- + 1/√n_u < π/√n_+ | PN learning · Finite-sample theoretical comparison | estimation error bound | Helped |
| Increase the amount of unlabeled data faster in order than the positive and negative sample sizes | PU and NU learning compared with PN learning · Asymptotic theoretical comparison | estimation error bound | Helped |
| Increase unlabeled data | PU learning · Benchmark datasets | misclassification rate | Helped |
| Increase unlabeled data | NU learning · Benchmark datasets | misclassification rate | No clear effect |
| Vary the class-prior probability π | PU, NU, and PN learning · Artificial and benchmark datasets | misclassification rate | Mixed |
Closest papers by meaning
- Learning from positive and unlabeled examples -Finite size sample bounds (NeurIPS 2025 · similarity 0.93)
- Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms (ICLR 2026 · similarity 0.93)
- Learning from Positive and Unlabeled Data with Arbitrary Positive Shift (NeurIPS 2020 · similarity 0.92)
- Positive and Unlabeled Learning with Controlled Probability Boundary Fence (ICML 2024 · similarity 0.89)
- Active Learning From Positive and Unlabeled Examples (NeurIPS 2026 · similarity 0.89)
- Surprises in Proper Positive-Only Learning (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.