Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
Preprint
Abstract
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).Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Lasagne: First Release.2015
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- One-shot learning of object categoriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989