Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
Keywords:(Deep) Neural Network Algorithms, Semi-Supervised Learning
AbstractThe drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations. It poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning methods with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing a novel alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify the proposed method yields significant improvements on robustness over state-of-the-art counterparts.
How to Cite
Wang, Q., Han, B., Liu, T., Niu, G., Yang, J., & Gong, C. (2021). Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 10183-10191. https://doi.org/10.1609/aaai.v35i11.17221
AAAI Technical Track on Machine Learning IV