Context-based Virtual Adversarial Training for Text Classification with Noisy Labels. (arXiv:2206.11851v1 [cs.CL])

Web: http://arxiv.org/abs/2206.11851

Deep neural networks (DNNs) have a high capacity to completely memorize noisy
labels given sufficient training time, and its memorization, unfortunately,
leads to performance degradation. Recently, virtual adversarial training (VAT)
attracts attention as it could further improve the generalization of DNNs in
semi-supervised learning. The driving force behind VAT is to prevent the models
from overfitting data points by enforcing consistency between the inputs and
the perturbed inputs. This strategy could be helpful in learning from noisy
labels if it …

arxiv classification context labels text text classification training virtual