Can I read Manifold Adversarial Learning on EtoBox?

Manifold Adversarial Learning by Zhang, Shufei; Huang, Kaizhu; Zhu, Jianke; Liu, Yang is a scholarly article available to read on EtoBox.

What is Manifold Adversarial Learning about?

Recently proposed adversarial training methods show the robustness to both adversarial and original examples and achieve state-of-the-art results in supervised and semi-supervised learning. All the existing adversarial training methods consider only how the worst perturbed examples (i.e., adversarial examples) could affect the model output. Despite their success, we argue that such setting may be in lack of generalization, since the output space (or label space) is apparently less informative.In this paper, we propose a novel method, called Manifold Adversarial Training (MAT). MAT manages to build an adversarial framework based on how the worst perturbation could affect the distributional manifold rather than the output space. Particularly, a latent data space with the Gaussian Mixture Model (GMM) will be first derived.On one hand, MAT tries to perturb the input samples in the way that would rough the distributional manifold the worst. On the other hand, the deep learning model is trained trying to promote in the latent space the manifold smoothness, measured by the variation of Gaussian mixtures (given the local perturbation around the data point). Importantly, since the latent sp

Author

Zhang, Shufei; Huang, Kaizhu; Zhu, Jianke; Liu, Yang

Published

2018

Language

EN