Learning Robust Variational Information Bottleneck with Reference

04/29/2021 ∙ by Weizhu Qian, et al. ∙ 0

We propose a new approach to train a variational information bottleneck (VIB) that improves its robustness to adversarial perturbations. Unlike the traditional methods where the hard labels are usually used for the classification task, we refine the categorical class information in the training phase with soft labels which are obtained from a pre-trained reference neural network and can reflect the likelihood of the original class labels. We also relax the Gaussian posterior assumption in the VIB implementation by using the mutual information neural estimation. Extensive experiments have been performed with the MNIST and CIFAR-10 datasets, and the results show that our proposed approach significantly outperforms the benchmarked models.



There are no comments yet.


page 6

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.