- Abstract: Generative Adversarial Networks are powerful generative models that can model the manifold of natural images. We leverage this property to perform manifold regularization by approximating a variant of the Laplacian norm using a Monte Carlo approximation that is easily computed with the GAN. When incorporated into the semi-supervised feature-matching GAN we achieve state-of-the-art results for semi-supervised learning on CIFAR-10 benchmarks when few labels are used, with a method that is significantly easier to implement than competing methods. We find that manifold regularization improves the quality of generated images, and is affected by the quality of the GAN used to approximate the regularizer.
- Keywords: semi-supervised learning, generative adversarial networks, manifold regularization