Search papers, labs, and topics across Lattice.
This paper introduces TRACE, a Two-Source Reliability Assessment framework that addresses the challenges of label noise in machine learning by evaluating both observed labels and model-derived pseudo targets independently. By analyzing loss fit, shallow relation stability, and prediction agreement for observed labels, alongside model confidence for pseudo targets, TRACE mitigates the risk of replacing one unreliable signal with another. The results demonstrate that TRACE significantly enhances the performance of refurbishment-based noisy-label learning, outperforming existing baselines on both synthetic and real-world datasets.
Relying on a single cleanliness score can lead to compounding errors in noisy-label learning, but TRACE uncouples the assessment of observed and pseudo labels for more reliable supervision.
Refurbishment-based noisy-label learning mixes an observed label with a model-derived pseudo target, typically using one sample-wise cleanliness score to control both branches. This creates a hidden coupling: reducing trust in the observed label automatically increases trust in the pseudo target. We show that this complementarity can replace one unreliable signal with another because a pseudo target learned from corrupted supervision may reproduce the noise it is meant to correct. Our representation diagnostics provide a consistent account of this mismatch: noisy supervision redirects deeper layers more strongly, whereas shallower relations remain comparatively stable and provide information beyond the loss posterior. We therefore propose TRACE, a Two-Source Reliability Assessment framework for Label Correction and Sample Reweighting. TRACE assesses the observed label using loss fit, shallow relation stability, and prediction agreement, while separately assessing the pseudo target using model confidence. Its source-specific scores control target correction and supervision strength without assuming complementary reliability. Across synthetic and real-world noisy benchmarks, TRACE improves representative refurbishment baselines and yields more reliable pseudo supervision.
