离群点作为枢纽，内群点作为辐条：面向双重不匹配半监督学习的统一潜在空间构建
Hub for Outliers, Spokes for Inliers: Uniform Latent Space Construction for Dual-Mismatched Semi-Supervised Learning
浏览论文内容
中文总结 AI 辅助
针对半监督学习中类别分布与标签空间双重不匹配问题，提出枢纽-辐条潜在几何结构，通过中心枢纽锚定未知类样本并均匀分布已知类，结合证据分类器提升特征判别性，实验最大提升3.25%。
中文摘要 AI 辅助
半监督学习通常假设标记数据和未标记数据共享相同的类别分布和标签空间。然而，这一假设经常被违反：未标记数据可能类别不平衡，并包含未知类别的样本，导致类别分布和标签空间均不匹配。这种双重不匹配会导致多数类主导潜在空间，而未知类别样本被过度自信地错误分类，从而降低特征判别性和伪标签质量。为解决这一问题，我们提出了一种枢纽-辐条潜在几何结构，其中已知类别围绕中心枢纽均匀分布，每个类别围绕其原型形成紧凑簇，而枢纽则为高不确定性的未知类别样本提供了一个专门设计的低证据区域锚点。结合基于证据的分类器，这种几何结构通过结构化特征组织减轻多数类主导，并引导高不确定性的未知类别样本向枢纽靠拢，最终增强特征判别性和不确定性分离。大量实验表明，我们的方法在各种设置下均优于最先进的方法，最大提升幅度达3.25%。
英文摘要
Semi-supervised learning typically assumes that labeled and unlabeled data share an identical class distribution and label space. However, this setting is often violated: unlabeled data may be imbalanced and contain unknown class samples, causing mismatches in both class distribution and label space. Such dual mismatch leads to majority classes dominating the latent space and unknown class samples being overconfidently misclassified, degrading feature discriminability and pseudo-label quality. To address this, we propose a hub-spoke latent geometry, where known classes are uniformly distributed around a central hub and each class forms compact clusters around its prototype, while the hub provides an anchor for a low-evidence region specifically designed for high-uncertainty unknown class samples. Integrated with an evidence-based classifier, this geometry ultimately enhances feature discriminability and uncertainty separation by mitigating majority-class domination through structured feature organization and guiding high-uncertainty unknown class samples toward the hub. Extensive experiments show that our method outperforms state-of-the-art methods, with a maximum improvement of 3.25% across various settings.
发表机构
- Southeast University（东南大学）
- Shandong Fundamental Research Center for Computer Science（山东基础计算机科学研究中心）
- Saint Francis University（圣方济各大学）
机构由 AI 辅助整理，请以论文原文为准。
