Probabilistic instance dependent label refinement for noisy label learning

Label refinement methods are designed to improve the quality of training labels by incorporating model predictions into the original training labels. By adjusting the combination coefficient of the noisy label, the impact of noise is reduced, which in turn makes the training process more robust. How...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Machine learning Jg. 114; H. 5; S. 120
Hauptverfasser: He, Hao-Yuan, Liu, Yu, Liu, Ren-Biao, Xie, Zheng, Li, Ming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.05.2025
Springer Nature B.V
Schlagworte:
Algorithms
Artificial Intelligence
Computer Science
Control
Labels
Machine Learning
Mechatronics
Natural Language Processing (NLP)
Neural networks
Noise generation
Optimization
Probability
Probability theory
Robotics
Simulation and Modeling
Statistical analysis
Deep neural networks
Instance-dependent noise
Machine learning
Classification
Noisy label learning
ISSN:0885-6125, 1573-0565
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Label refinement methods are designed to improve the quality of training labels by incorporating model predictions into the original training labels. By adjusting the combination coefficient of the noisy label, the impact of noise is reduced, which in turn makes the training process more robust. However, previous label refinement methods are unable to model instance-dependent noise, which is the most realistic type of noise. To address this limitation, we propose a simple approach, probabilistic instance-dependent label refinement (referred to as π -LR). Inspired by the fact that humans are more likely to make mistakes when annotating confusing instances, we propose to estimate the probability of whether a sample is confusing, which can be useful for modeling noise generation. Our approach exploits this concept by assigning a confusing probability η i to each instance x i from a probabilistic perspective. This provides a clear understanding of how instance-dependent noise affects true labels. Empirical evaluations show that π -LR improves the robustness of the model in the presence of label noise and outperforms all compared methods on both realistic and synthetic label noise, while maintaining high efficiency in time and space.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0885-6125
1573-0565
DOI:10.1007/s10994-024-06668-y