ACD-U: Asymmetric co-teaching with machine unlearning for robust learning with noisy labels

• URL: http://arxiv.org/abs/2603.07166v1
• Date: Sat, 07 Mar 2026 12:13:14 GMT
• Title: ACD-U: Asymmetric co-teaching with machine unlearning for robust learning with noisy labels
• Abstract summary: Deep neural networks are prone to memorizing incorrect labels during training, which degrades their generalizability.<n>We propose asymmetric co-teaching with different architectures (ACD)-U, an asymmetric co-teaching framework that uses different model architectures and incorporates machine unlearning.<n>ACD-U addresses this limitation through two core mechanisms. First, its asymmetric co-teaching pairs a contrastive language-image pretraining (CLIP)-pretrained vision Transformer with a convolutional neural network (CNN)<n>Second, selective unlearning enables post-hoc error correction by identifying incorrectly memorized samples through loss trajectory analysis and CLI
• Score: 2.0391237204597363
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep neural networks are prone to memorizing incorrect labels during training, which degrades their generalizability. Although recent methods have combined sample selection with semi-supervised learning (SSL) to exploit the memorization effect -- where networks learn from clean data before noisy data -- they cannot correct selection errors once a sample is misclassified. To overcome this, we propose asymmetric co-teaching with different architectures (ACD)-U, an asymmetric co-teaching framework that uses different model architectures and incorporates machine unlearning. ACD-U addresses this limitation through two core mechanisms. First, its asymmetric co-teaching pairs a contrastive language-image pretraining (CLIP)-pretrained vision Transformer with a convolutional neural network (CNN), leveraging their complementary learning behaviors: the pretrained model provides stable predictions, whereas the CNN adapts throughout training. This asymmetry, where the vision Transformer is trained only on clean samples and the CNN is trained through SSL, effectively mitigates confirmation bias. Second, selective unlearning enables post-hoc error correction by identifying incorrectly memorized samples through loss trajectory analysis and CLIP consistency checks, and then removing their influence via Kullback--Leibler divergence-based forgetting. This approach shifts the learning paradigm from passive error avoidance to active error correction. Experiments on synthetic and real-world noisy datasets, including CIFAR-10/100, CIFAR-N, WebVision, Clothing1M, and Red Mini-ImageNet, demonstrate state-of-the-art performance, particularly in high-noise regimes and under instance-dependent noise. The code is publicly available at https://github.com/meruemon/ACD-U.

Related papers

• Initialization Matters: Unraveling the Impact of Pre-Training on Federated Learning [21.440470901377182]
  Initializing with pre-trained models is becoming standard practice in machine learning.<n>We study the class of two-layer convolutional neural networks (CNNs) and provide bounds on the training error convergence and test error of such a network trained with FedAvg.
  arXiv  Detail & Related papers  (2025-02-11T23:53:16Z)
• AsyCo: An Asymmetric Dual-task Co-training Model for Partial-label Learning [53.97072488455662]
  Self-training models achieve state-of-the-art performance but suffer from error accumulation problem caused by mistakenly disambiguated instances. We propose an asymmetric dual-task co-training model called AsyCo, which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly. Experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.
  arXiv  Detail & Related papers  (2024-07-21T02:08:51Z)
• A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification [51.35500308126506]
  Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. We study how classification-based evaluation protocols for SSL correlate and how well they predict downstream performance on different dataset types.
  arXiv  Detail & Related papers  (2024-07-16T23:17:36Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning [76.00798972439004]
  Collaborative Sample Selection (CSS) removes noisy samples from identified clean set. We introduce a co-training mechanism with a contrastive loss in semi-supervised learning.
  arXiv  Detail & Related papers  (2023-10-24T05:37:20Z)
• Determination of the critical points for systems of directed percolation class using machine learning [0.0]
  We use CNN and DBSCAN in order to determine the critical points for directed bond percolation (bond DP) model and Domany-Kinzel cellular universality (DK) model. Our results from both algorithms show that, even for a very small values of lattice size, machine can predict the critical points accurately for both models.
  arXiv  Detail & Related papers  (2023-07-19T20:58:12Z)
• Learning from Data with Noisy Labels Using Temporal Self-Ensemble [11.245833546360386]
  Deep neural networks (DNNs) have an enormous capacity to memorize noisy labels. Current state-of-the-art methods present a co-training scheme that trains dual networks using samples associated with small losses. We propose a simple yet effective robust training scheme that operates by training only a single network.
  arXiv  Detail & Related papers  (2022-07-21T08:16:31Z)
• Synergistic Network Learning and Label Correction for Noise-robust Image Classification [28.27739181560233]
  Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. We propose a robust label correction framework combining the ideas of small loss selection and noise correction. We demonstrate our method on both synthetic and real-world datasets with different noise types and rates.
  arXiv  Detail & Related papers  (2022-02-27T23:06:31Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)
• Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks [14.685237010856953]
  We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. We show that learning can be performed with one of two more plausible alternatives to backpagation.
  arXiv  Detail & Related papers  (2021-09-30T12:56:57Z)
• Self-Damaging Contrastive Learning [92.34124578823977]
  Unlabeled data in reality is commonly imbalanced and shows a long-tail distribution. This paper proposes a principled framework called Self-Damaging Contrastive Learning to automatically balance the representation learning without knowing the classes. Our experiments show that SDCLR significantly improves not only overall accuracies but also balancedness.
  arXiv  Detail & Related papers  (2021-06-06T00:04:49Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.