Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
For practitioners training models with noisy labels, this work provides a more reliable way to distinguish hard clean samples from mislabeled ones, improving model accuracy.
The paper identifies that existing noisy-label methods using forward-space signals (loss, confidence) cannot distinguish hard clean samples from mislabeled ones because they have similar loss but induce different parameter updates. The authors propose Relative Geometric Conflict (RGC), which compares the observed-label gradient with a teacher gradient to diagnose update reliability, improving hard-clean preservation and accuracy on noisy-label benchmarks.
Noisy-label methods often estimate sample reliability from forward-space signals such as loss, confidence, or entropy. These signals indicate whether a sample is difficult to predict, but they do not directly test whether its observed label induces a reliable parameter update. This gap matters because hard clean samples and mislabeled samples can have similar loss while inducing different updates. We recast reliability estimation as diagnosis of the observed-label update. The sample-wise empirical Fisher trace gives a backward-space measure of update energy: for the classifier layer, it factorizes into a prediction-residual term and a feature-sensitivity term, so it captures information beyond scalar loss. Trace, however, is still a radial magnitude signal and cannot decide whether a large update is useful or harmful. We therefore propose Relative Geometric Conflict (RGC), which compares the observed-label gradient with a reference gradient induced by an EMA teacher. The conflict term helps distinguish large but aligned hard-clean updates from large conflicting updates caused by corrupted labels. Across synthetic and real-world noisy-label benchmarks, RGC improves hard-clean preservation and accuracy under our evaluation protocol.