Research
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
arXiv:2607.11947v1 Announce Type: cross Abstract: Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated. While PNU l
arXiv:2607.11947v1 Announce Type: cross Abstract: 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.
Related
- A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees
- Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
- Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss
Source: arXiv cs.AI | 2026-07-15