SOURCE-LINKED INTELLIGENCE

Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Standard cross-entropy loss causes neural networks trained on ordinal classification tasks to hedge predictions toward center classes, a failure mode we term \emph{center-class hedging}. This occurs because predicting the middle class minimizes expected symmetric loss, making it the path of least resistance regardless of the true label. Existing ordinal losses address related problems such as large-error penalization and rank consistency, but none directly suppresses center-class hedging as a function of where the true label lies relative to the ordinal center. We propose the Adaptive Margin O

Read original source ↗ Open in workspace

recordType

paper

region

Global