mlsanityData to 14 Oct 2026

COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement

arXiv 2506.19496 ↗First posted 24 Jun 2025cs.LGcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Large deep learning models have achieved significant success in various tasks. However, the performance of a model can significantly degrade if it is needed to train on datasets with noisy labels with misleading or ambiguous information. To date, there are limited investigations on how to restore performance when model degradation has been incurred by noisy label data. Inspired by the ``forgetting mechanism'' in neuroscience, which enables accelerating the relearning of correct knowledge by unlearning the wrong knowledge, we propose a robust model restoration and refinement (MRR) framework COLUR, namely Confidence-Oriented Learning, Unlearning and Relearning. Specifically, we implement COLUR with an efficient co-training architecture to unlearn the influence of label noise, and then refine model confidence on each label for relearning. Extensive experiments are conducted on four real datasets and all evaluation results show that COLUR consistently outperforms other SOTA methods after MRR.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 38 of its 56 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

38 of 56 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Machine Unlearning via Null Space Calibration21 Apr
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  3. 2023Model Sparsity Can Simplify Machine Unlearning11 Apr
  4. 2022Evaluating Machine Unlearning via Epistemic Uncertainty23 Aug
  5. 2021Machine Unlearning of Features and Labels26 Aug

Other references · 33

  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2016Wide Residual Networkscited by 3,070
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  6. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  7. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  8. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  9. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  10. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  11. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
21 more
  1. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  2. 2020Amnesiac Machine Learningcited by 319
  3. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  4. 2020Approximate Data Deletion from Machine Learning Modelscited by 255
  5. 2017Decoupling "when to update" from "how to update"cited by 230
  6. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  7. 2020Does label smoothing mitigate label noise?cited by 204
  8. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  9. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  10. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  11. 2019Image Classification with Deep Learning in the Presence of Noisy Labels: A Surveycited by 101
  12. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  13. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  14. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  15. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  16. 2020MoPro: Webly Supervised Learning with Momentum Prototypescited by 66
  17. 2021Learning with Noisy Labels via Sparse Regularizationcited by 39
  18. 2024NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstructioncited by 26
  19. 2020Noisy Concurrent Training for Efficient Learning under Label Noisecited by 13
  20. 2023Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networkscited by 7
  21. 2024Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networkscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction
  2. 2026Why Some Models Resist Unlearning: A Linear Stability Perspective
  3. 2024Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models
  4. 2024On Effects of Steering Latent Representation for Large Language Model Unlearning
  5. 2026Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction
  6. 2025Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models
  7. 2024Learning to Unlearn for Robust Machine Unlearning
  8. 2026The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples