Semi supervised learning improves by separating known and unknown classes
Hub for Outliers, Spokes for Inliers: Uniform Latent Space Construction for Dual-Mismatched Semi-Supervised Learning
Machine Learning
Summary
Machine learning often learns from a mix of labeled and unlabeled data, assuming both are similar. However, unlabeled data can have unknown or uneven classes, confusing the learning process. The authors propose organizing data into a 'hub and spokes' pattern, where known classes form tight groups around their own points while unknown data collects in the center hub. This helps the system better distinguish known from unknown samples, resulting in improved learning accuracy. Their experiments show this method performs better than previous approaches.
What this means in practice
- •For machine learning engineers: Improve semi-supervised models to better handle unlabeled data with unknown or imbalanced classes by structuring latent features with a hub-spoke geometry.
- •For data platform developers: Build data pipelines that incorporate this feature organization to boost classification accuracy when labeled data are scarce or noisy and unlabeled data contain unknown categories.
Authors
Li Yuan, Yaxin Hou, Jiawei Tang, Yongbiao Gao, Yuheng Jia
Abstract
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.