PGASL: Predictive and Generative Adversarial Semi-supervised Learning for imbalanced data

Ru Huang, Yunlong Wang, Ruoxin Li, Wei Huang, Emily Zhao, Yilian Yuan

Keywords: semi-supervised learning, imbalanced learning, GAN model, adversarial learning

Abstract: Modern machine learning techniques often suffer from class imbalance where only a small amount of data is available for minority classes. Classifiers trained on an imbalanced dataset, although have high accuracy on majority classes, can perform poorly on minority classes. This is problematic when minority classes are also important. Generative Adversarial Networks (GANs) have been proposed for generating artificial minority examples to balance the training. We propose a class-imbalanced semi-supervised learning algorithm PGASL which can be efficiently trained on unlabeled and class-imbalanced data. In this work, we use a predictive network which is trained adversarially for the discriminator to correct predictions on the unlabeled dataset. Experiments on text datasets show that PGASL outperforms state-of-the-art class-imbalanced learning algorithms by including both predictive network and generator.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)