基于风险重写的广义无分布半监督学习
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
浏览论文内容
中文总结 AI 辅助
研究针对半监督学习方法依赖分布假设的问题，提出基于组件风险线性组合构建无偏风险估计器的广义框架，推导最小可实现方差，建立泛化界，并引入两种实用方法，在多分类基准测试中表现良好。
中文摘要 AI 辅助
典型的半监督学习（SSL）方法依赖分布假设，假设不成立时性能会下降。虽然风险重写方法PNU学习提供了无分布替代方案，但它仅限于二分类且方差最优性不明。本文提出一个广义框架，通过组件风险的线性组合构建无偏风险估计器，包含PNU学习并扩展到多分类。我们推导了最小可实现方差，表明在非对称损失场景下我们的估计器方差比PNU更低。此外，我们建立了泛化界，将方差降低与学习性能提升直接联系起来。基于这些理论见解，我们引入两种实用的SSL方法，在二分类和多分类基准测试中经验性地匹配或优于现有方法。
英文摘要
Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated. While PNU learning, a risk rewriting method, offers a distribution-free alternative, it is restricted to binary classification and its variance optimality remains unclear. In this paper, we propose a generalized framework that constructs unbiased risk estimators using linear combinations of component risks, subsuming PNU learning and extending to multiclass classification. We derive the minimum achievable variance, demonstrating our estimator can attain lower variance than PNU in asymmetric loss scenarios. Furthermore, we establish a generalization bound directly linking this variance reduction to improved learning performance. Based on these theoretical insights, we introduce two practical SSL methods that empirically match or outperform existing approaches on binary and multiclass benchmarks.
发表机构
- Institute of Science Tokyo（东京理科大学）
- RIKEN Center for Advanced Intelligence Project（理化学研究所高级智能项目中心）
机构由 AI 辅助整理，请以论文原文为准。
