Research map / Label-efficient and robust learning / Recognition and long-tail
PULNS: Positive-Unlabeled Learning with Effective Negative Sample Selector
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 PULNS with an optimized negative sample selector instead of the strongest listed baseline | PU learning · All seven benchmarks, γ=0.2, 0.4, 0.6 | error rate (%) | Helped |
| Add the learned negative sample selector rather than use PULNS alt without it (ablation) | PULNS · All seven benchmarks, γ=0.2, 0.4, 0.6 | error rate (%): CIFAR-10: 12.92 -> 7.98 (γ=0.2), 18.84 -> 11.44 (γ=0.4), 48.26 -> 11.73 (γ=0.6); MNIST: 7.48 -> 3.63 (γ=0.2), 12.28 -> 5 | Helped |
| Optimize the selector through PULNS reinforcement learning rather than use the five comparison selectors | Negative sample selection · mushrooms, shuttle, spambase, usps, landsat; γ=0.2, 0.4, 0.6 | NPV and TNR (%) | Helped |
Closest papers by meaning
- Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms (ICLR 2026 · similarity 0.92)
- Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning (NeurIPS 2025 · similarity 0.91)
- Learning from Positive and Unlabeled Data with a Selection Bias (ICLR 2019 · similarity 0.91)
- Learning from positive and unlabeled examples -Finite size sample bounds (NeurIPS 2025 · similarity 0.89)
- Positive and Unlabeled Learning with Controlled Probability Boundary Fence (ICML 2024 · similarity 0.89)
- Active Learning From Positive and Unlabeled Examples (NeurIPS 2026 · similarity 0.86)
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.