Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning

Citations Over TimeTop 1% of 2018 papers

Abstract

We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adversarial training, our method defines the adversarial direction without label information and is hence applicable to semi-supervised learning. Because the directions in which we smooth the model are only "virtually" adversarial, we call our method virtual adversarial training (VAT). The computational cost of VAT is relatively low. For neural networks, the approximated gradient of virtual adversarial loss can be computed with no more than two pairs of forward- and back-propagations. In our experiments, we applied VAT to supervised and semi-supervised learning tasks on multiple benchmark datasets. With a simple enhancement of the algorithm based on the entropy minimization principle, our VAT achieves state-of-the-art performance for semi-supervised learning tasks on SVHN and CIFAR-10.

Related Papers

• → A risk degree-based safe semi-supervised learning algorithm(2015)15 cited
• → Empowering Imbalanced Data in Supervised Learning: A Semi-supervised Learning Approach(2014)5 cited
• → Recommender system designed using an ensemble approach to semi-supervised learning(2022)1 cited
• → A safe semi-supervised kernel minimum squared error algorithm(2015)
• Weakly Supervised Learning: What Could It Do and What Could Not?(2010)