解决标签选择偏差的正负样本学习新方法
PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
- 用归一化倾向得分和逆概率加权改进正负样本学习
- 在非均匀标签分布下比基线方法准确率更高
- 适合存在标签偏差的真实数据场景
正负样本（PU）学习旨在仅用少量标记正例和大量未标记样例实现高精度二分类。现有基于代价敏感的方法常依赖强假设，即正例标签是完全随机选取的。事实上，真实世界中的标签分布往往不均，表明大多数正例和未标记数据都受选择偏差影响。本文基于Bekker等人提出的SAR-PU倾向得分加权框架，提出一种新的正负样本学习增强框架PUe，采用归一化倾向得分与归一化逆概率加权（NIPW）。主要贡献包括：归一化逆概率加权的PU风险公式；对带偏标签下样本加权误差及常见PU估计器的理论分析；正则化深度倾向得分估计；与现代代价敏感PU方法的集成；支持选择性标注负类。在MNIST、CIFAR-10和ADNI上的实验表明，在非均匀标签分布下，该方法显著优于多个基线。
原文摘要 · Abstract (English)
Positive-Unlabeled (PU) learning aims to achieve high-accuracy binary classification with limited labeled positive examples and numerous unlabeled ones. Existing cost-sensitive-based methods often rely on strong assumptions that examples with an observed positive label were selected entirely at random. In fact, the uneven distribution of labels is prevalent in real-world PU problems, indicating that most actual positive and unlabeled data are subject to selection bias. Building on the SAR-PU propensity-weighted framework of Bekker et al., we study a PU learning enhancement (PUe) framework using normalized propensity scores and normalized inverse probability weighting (NIPW). PUe's main contributions are a normalized inverse-probability-weighted PU risk formulation; additional theoretical analyses of normalized sample-weight error and common PU estimators under biased labeling; regularized deep propensity-score estimation; integration with modern cost-sensitive PU methods; and support for selectively labeled negative classes. Experiments on MNIST, CIFAR-10, and ADNI demonstrate improvements over several PU baselines under non-uniform label distributions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。