Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
This work addresses the challenge of unsupervised and semi-supervised learning for classification, offering an incremental improvement by integrating GAN and RIM frameworks.
The paper tackles the problem of learning discriminative classifiers from unlabeled or partially labeled data by introducing CatGAN, which combines mutual information maximization with adversarial robustness, and demonstrates its effectiveness on synthetic and image classification tasks with robust performance.
In this paper we present a method for learning a discriminative classifier from unlabeled or partially labeled data. Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an adversarial generative model. The resulting algorithm can either be interpreted as a natural generalization of the generative adversarial networks (GAN) framework or as an extension of the regularized information maximization (RIM) framework to robust classification against an optimal adversary. We empirically evaluate our method - which we dub categorical generative adversarial networks (or CatGAN) - on synthetic data as well as on challenging image classification tasks, demonstrating the robustness of the learned classifiers. We further qualitatively assess the fidelity of samples generated by the adversarial generator that is learned alongside the discriminative classifier, and identify links between the CatGAN objective and discriminative clustering algorithms (such as RIM).