cs.LGNov 7, 2026

Dual-Granularity Learning for Regression with Continuous Noisy Labels

Authors: Hui Guo, Boyu Wang, Grace Y. Yi

Organizations: Department of Computer Science, University of Western Ontario · Vector Institute · Department of Statistical and Actuarial Sciences, University of Western Ontario

Abstract

Learning with noisy labels has been extensively studied for classification, yet its regression counterpart remains relatively underexplored. Unlike classification, regression involves continuous-valued targets where label noise exhibits heterogeneous magnitudes across instances, which poses conflicting requirements on the model: correcting small-to-moderate deviations requires sensitivity to label values for instance-level refinement, whereas large deviations caused by corrupted or outlying annotations render exact label values unreliable, necessitating reduced reliance on exact labels and instead leveraging ordinal structure among samples. These requirements call for methods that capture both global structure and sample-specific deviations in a unified manner. To this end, we propose GRAIN, a dual-granularity framework for robust noisy regression. At the fine-grained level, we derive an explicit residual learning mechanism from a robust loss formulation, introducing instance-specific auxiliary variables to decouple label noise from predictive signals. At the coarse-grained level, we introduce a binning-based contrastive regularization that enforces an order-preserving feature structure aligned with label proximity, addressing noise beyond the capacity of local residual refinement. The two levels are coupled via a histogram-based bridging mechanism that enables bidirectional information flow: coarse-grained structural guidance establishes a well-ordered feature space that anchors residual learning, while fine-grained residual refinement corrects instance-level deviations that structural regularization alone cannot resolve. Experimental results show that GRAIN consistently improves robustness and generalization under diverse noise conditions.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Variational Rectification Inference for Learning with Noisy Labels

    Mar 18, 2026Haoliang Sun, Qi Wei, Lei Feng +4Learning with Noisy LabelsVariational Inference

  2. Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise

    Apr 7, 2026Yuanjie Shi, Peihong Li, Zijian Zhang +2Margin-Based LearningLearning with Noisy Labels

  3. ITBoost: Information-Theoretic Trust for Robust Boosting

    May 6, 2026Ye Su, Longlong Zhao, Diego Garcia-Gil +4Gradient-Boosted Decision TreesEnsemble Learning