Research map / Label-efficient and robust learning / Recognition and long-tail
Estimating the Class Prior in Positive and Unlabeled Data Through Decision Tree Induction
Jessa Bekker, Jesse Davis
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 |
|---|---|---|---|
| TIcE decision-tree lower-bound estimator instead of kernel MPE (KM2) | class prior estimation · 11 PU datasets | average absolute error: 0.10 -> 0.09 | Improved |
| TIcE instead of KM2 | class prior estimation · 11 PU datasets | time per example: 47.28 -> 0.76 | Improved |
| take maximum lower bound over subdomains instead of single most promising subdomain (ablation) | TIcE · PU datasets | absolute error | Improved |
| increase TR above default (125-150%) (ablation) | TIcE · 11 PU datasets | absolute error: 0.090 -> 0.170 | Hurt |
| decrease TR to 50-75% of default (ablation) | TIcE · 11 PU datasets | absolute error: 0.090 -> 0.092 | No clear effect |
Closest papers by meaning
- Class Prior Estimation with Biased Positives and Unlabeled Examples (AAAI 2020 · similarity 0.90)
- Learning from Positive and Unlabeled Data without Explicit Estimation of Class Prior (AAAI 2020 · similarity 0.88)
- Recovering True Classifier Performance in Positive-Unlabeled Learning (AAAI 2017 · similarity 0.88)
- Fast Nonparametric Estimation of Class Proportions in the Positive-Unlabeled Classification Setting (AAAI 2020 · similarity 0.88)
- Learning from positive and unlabeled examples -Finite size sample bounds (NeurIPS 2025 · similarity 0.87)
- Can Class-Priors Help Single-Positive Multi-Label Learning? (NeurIPS 2025 · similarity 0.85)
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.
