arXiv Machine Learning
Focused PU learning from imbalanced data
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 16
Imbalanced Classification under Capacity Constraints
arXiv:2605. 03289v2 Announce Type: replace-cross Abstract: Detecting observations from a minority class under severe class imbalance is a central challenge in applications such as fraud detection, medical screening, and industrial quality control.
arXiv Machine Learning
Jul 14
RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classification
arXiv:2607. 09816v1 Announce Type: new Abstract: Class imbalance poses a fundamental challenge in risk-sensitive applications such as fraud detection and medical diagnosis, where minority-class samples are scarce yet critical for accurate classification.
arXiv AI
2d ago
Partial AUC Maximization from Positive-unlabeled Data
arXiv:2610.00284v1 Announce Type: cross Abstract: The partial area under the receiver operating characteristic curve (pAUC) is an important performance metric for binary classification that summarize...
arXiv Machine Learning
Sep 11
AUC Maximization from Biased Positive-unlabeled Data with Confidence
The paper introduces a method for maximizing the area under the receiver operating characteristic curve (AUC) when only biased positive and unlabeled (PU) data are available. It leverages confidence scores—probabilities that an instance is positive—associated with a small set of labeled positives to derive an AUC risk estimator that accounts for bias. Experiments on eight real-world datasets demonstrate the method’s effectiveness.
arXiv Machine Learning
Jul 16
PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
arXiv:2607. 13428v1 Announce Type: new Abstract: Positive-Unlabeled (PU) learning aims to achieve high-accuracy binary classification with limited labeled positive examples and numerous unlabeled ones.
arXiv Machine Learning
5d ago
Tabular Imbalanced Learning: A Survey, Benchmark, and Practical Guide
The paper surveys tabular imbalanced learning and introduces TILBench, a benchmark evaluating over 40 methods on 57 datasets. It presents a unified taxonomy of approaches and shows that no single method dominates across all settings, with performance depending on dataset regimes and computational constraints. Practical recommendations for method selection and future research directions are provided.