标题： 带有虚拟对抗训练的分布平滑 显示英文标题

标题： Distributional Smoothing with Virtual Adversarial Training

摘要： 我们提出局部分布平滑性（LDS），这是统计模型的一种新的平滑性概念，可以用作正则化项，以促进模型分布的平滑性。 我们将基于LDS的正则化称为虚拟对抗训练（VAT）。 在输入数据点处的模型的LDS定义为模型分布对围绕该数据点的局部扰动的基于KL散度的鲁棒性。 VAT类似于对抗训练，但其不同之处在于它仅从模型分布中确定对抗方向，而不使用标签信息，使其适用于半监督学习。 VAT的计算成本相对较低。 对于神经网络，LDS的近似梯度可以通过不超过三对前向和反向传播来计算。 当我们将我们的技术应用于MNIST数据集的监督和半监督学习时，它优于除当前最先进的方法以外的所有训练方法，该方法基于高度先进的生成模型。 我们还将我们的方法应用于SVHN和NORB，并确认了我们的方法在这些数据集上应用的当前最先进的半监督方法中的优越性能。 显示英文摘要

摘要： We propose local distributional smoothness (LDS), a new notion of smoothness for statistical model that can be used as a regularization term to promote the smoothness of the model distribution. We named the LDS based regularization as virtual adversarial training (VAT). The LDS of a model at an input datapoint is defined as the KL-divergence based robustness of the model distribution against local perturbation around the datapoint. VAT resembles adversarial training, but distinguishes itself in that it determines the adversarial direction from the model distribution alone without using the label information, making it applicable to semi-supervised learning. The computational cost for VAT is relatively low. For neural network, the approximated gradient of the LDS can be computed with no more than three pairs of forward and back propagations. When we applied our technique to supervised and semi-supervised learning for the MNIST dataset, it outperformed all the training methods other than the current state of the art method, which is based on a highly advanced generative model. We also applied our method to SVHN and NORB, and confirmed our method's superior performance over the current state of the art semi-supervised method applied to these datasets.