解决半监督回归中伪标签不可靠的问题，提升模型稳定性与精度。
Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
- 基于双层优化动态调整伪标签权重，考虑输出不确定性。
- 在多个基准数据集上显著优于现有方法，误差更低且更稳健。
- 适合处理带异方差噪声的回归任务，尤其适用于标注数据少的场景。
伪标签是半监督学习中的常用范式，但在半监督回归（SSR）中应用仍较少。与分类任务中离散且可信心过滤的伪标签不同，回归任务输出为连续值且存在异方差噪声，难以评估伪标签可靠性。因此，简单使用伪标签易导致误差累积和过拟合。为此，我们提出一种基于不确定性的伪标签框架，从双层优化视角动态调节伪标签影响。通过联合最小化所有数据的经验风险，并优化不确定性估计以增强标记数据上的泛化能力，该方法有效缓解了不可靠伪标签的影响。我们提供了理论分析，并在多个基准 SSR 数据集上进行了广泛实验，结果表明本方法在鲁棒性和性能上均优于现有方法。代码已开源：https://github.com/sxq/Heteroscedastic-Pseudo-Labels。
原文摘要 · Abstract (English)
Pseudo-labeling is a commonly used paradigm in semi-supervised learning, yet its application to semi-supervised regression (SSR) remains relatively under-explored. Unlike classification, where pseudo-labels are discrete and confidence-based filtering is effective, SSR involves continuous outputs with heteroscedastic noise, making it challenging to assess pseudo-label reliability. As a result, naive pseudo-labeling can lead to error accumulation and overfitting to incorrect labels. To address this, we propose an uncertainty-aware pseudo-labeling framework that dynamically adjusts pseudo-label influence from a bi-level optimization perspective. By jointly minimizing empirical risk over all data and optimizing uncertainty estimates to enhance generalization on labeled data, our method effectively mitigates the impact of unreliable pseudo-labels. We provide theoretical insights and extensive experiments to validate our approach across various benchmark SSR datasets, and the results demonstrate superior robustness and performance compared to existing methods. Our code is available at https://github.com/sxq/Heteroscedastic-Pseudo-Labels.
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。