SOURCE-LINKED INTELLIGENCE

Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the pseudo-labels that are then used to update the model. In the cold-start regime, where at most a few labels per class are available, this coupling is ill-posed, since the classifier cannot supervise itself before it has learned. To address this problem, we propose VAST (Veracity-Aware Semi-Supervised Training), which decouples these two stages. Probabilistic beliefs over the unlabeled set are first inferred directly from the geometry of a frozen self

Read original source ↗ Open in workspace

recordType

paper

region

Global