arXiv Machine Learning
Jun 8
An Adaptive Data cleaning Framework for Noisy Label Detection
arXiv:2606. 07086v1 Announce Type: cross Abstract: Deep neural networks (DNNs) excel in computer vision tasks given large annotated datasets.
Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction
The paper compares five machine unlearning (MU) methods—NegGrad, Fine‑Tuning (FT), Random Labeling (RL), SalUn, and MUNBa—on noisy‑label correction across CIFAR‑10, CIFAR‑100, and Food‑101N. Results show that the best MU strategy depends on the noise type: FT works well for most closed‑set noise, RL and SalUn are robust and nearly match retraining accuracy under instance‑dependent noise, while MUNBa excels only under extreme symmetric noise. In open‑set noise, retraining on the cleaned data actually hurts performance, indicating that approximating retraining is not suitable in that regime, yet all MU methods still achieve near‑retraining accuracy on Food‑101N with much lower runtime.
Related stories
arXiv AI
Jun 11
Noise-Aware Framework for Correcting Corrupted Labels
arXiv:2606. 11695v1 Announce Type: cross Abstract: High-quality labeled data is essential for training reliable ML/DL models.
arXiv Machine Learning
Jul 14
Random Label Prediction Heads for Studying Memorization in Deep Neural Networks
arXiv:2607. 11541v1 Announce Type: new Abstract: We introduce a straightforward yet effective method to empirically study memorization in deep neural networks for classification tasks.
arXiv Machine Learning
Jul 17
Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance
arXiv:2607. 14466v1 Announce Type: new Abstract: Noise injection is a well-known technique in stochastic optimization.
arXiv Machine Learning
Jun 16
Benchmarking Instance-Dependent Label Noise with Controlled Corruptions
arXiv:2606. 14965v1 Announce Type: new Abstract: Synthetic instance-dependent label noise (IDN) benchmarks are widely used to evaluate noisy-label learning methods, yet existing approaches typically generate noise through imperfect annotators or classifier raters, leaving the source of ambiguity implicit.
arXiv AI
Jun 2
PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
arXiv:2604. 05634v2 Announce Type: replace Abstract: Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation.
arXiv Machine Learning
Jul 21
Orthogonal Gradient Constraints Shape Noisy-Label Memorization Dynamics
arXiv:2607. 16231v1 Announce Type: new Abstract: Modern neural networks can fit corrupted training labels, making noisy-label learning a useful setting for studying memorization-driven overfitting.
arXiv Machine Learning
Jun 11
A Data-Centric Framework for Detecting and Correcting Corrupted Labels
arXiv:2606. 11699v1 Announce Type: new Abstract: The performance of machine learning and deep learning models largely depends on the quality of the training data.
arXiv AI
Jun 9
LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty
arXiv:2503. 18314v5 Announce Type: replace-cross Abstract: We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch.
arXiv AI
Jun 29
Applicability of memorization indicators for early spotting of overfitting while recalibrating sEMG-decoders on low sample sizes
arXiv:2606. 27855v1 Announce Type: cross Abstract: Deep learning models for surface electromyography (sEMG) can benefit substantially from subject-specific (re-)calibration, since no sufficiently large and diverse datasets are available to train fully generic decoders.
arXiv Machine Learning
Jun 5
Towards Label-Noise Resistant Learning via Optimal Brain Damage Masking
arXiv:2508. 09697v3 Announce Type: replace Abstract: Noisy labels are inevitable in real-world scenarios.
arXiv Machine Learning
1d ago
Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning
The paper investigates whether a model that has undergone class unlearning can still recover forgotten classes without access to original data. It introduces a white‑box audit method that generates synthetic probes in representation space, filters them by confidence, and relabels boundary‑adjacent probes as the forgotten class. The authors define a Relearning Score to quantify recovery while preserving retain performance, and demonstrate that several unlearning techniques on CIFAR‑10, CIFAR‑100, and TinyImageNet can be fully recovered in a source‑free setting, sometimes even outperforming a retrained reference.