MarginGAN: Adversarial Training in Semi-Supervised Learning
A Margin Generative Adversarial Network (MarginGAN) is proposed for semi-supervised learning problems. Like Triple-GAN, the proposed MarginGAN consists of three components---a generator, a discriminator and a classifier, among which two forms of adversarial training arise. The discriminator is trained as usual to distinguish real examples from fake examples produced by the generator. The new feature is that the classifier attempts to increase the margin of real examples and to decrease the margin of fake examples. On the contrary, the purpose of the generator is yielding realistic and large-margin examples in order to fool the discriminator and the classifier simultaneously. Pseudo labels are used for generated and unlabeled examples in training. Our method is motivated by the success of large-margin classifiers and the recent viewpoint that good semi-supervised learning requires a ``bad'' GAN. Experiments on benchmark datasets testify that MarginGAN is orthogonal to several state-of-the-art methods, offering improved error rates and shorter training time as well.
Code (1)
Tasks
Generative Adversarial NetworkMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Learning for Supervised and Semi-supervised Relation Extraction in Biomedical Literature
Adversarial training is a technique of improving model performance by involving adversarial examples in the training process. In this paper, we investigate adversarial training with multiple adversarial examples to benef…
BenchmarkingRelationRelation ExtractionVirtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the …
Semi-Supervised Image ClassificationAdversarial Training Methods for Semi-Supervised Text Classification
Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both metho…
ClassificationGeneral ClassificationSemi-Supervised Text ClassificationSentiment Analysis+2Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation
Adversarial robustness is a research area that has recently received a lot of attention in the quest for trustworthy artificial intelligence. However, recent works on adversarial robustness have focused on supervised lea…
Adversarial RobustnessKnowledge DistillationImprove Training Stability of Semi-supervised Generative Adversarial Networks with Collaborative Training
Improved generative adversarial network (Improved GAN) is a successful method of using generative adversarial models to solve the problem of semi-supervised learning. However, it suffers from the problem of unstable trai…
General ClassificationGenerative Adversarial Network