Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning
This work addresses the lack of adversarial example methods for unsupervised learning, offering a novel tool for data augmentation that benefits researchers and practitioners in unsupervised ML, though it is incremental in extending adversarial techniques to this domain.
The paper tackles the problem of generating adversarial examples for unsupervised machine learning models, proposing a framework that uses mutual information and a MinMax algorithm to create these examples without supervision, and demonstrates that using them as data augmentation improves performance across tasks like data reconstruction and representation learning, with significant gains observed.
Adversarial examples causing evasive predictions are widely used to evaluate and improve the robustness of machine learning models. However, current studies focus on supervised learning tasks, relying on the ground-truth data label, a targeted objective, or supervision from a trained classifier. In this paper, we propose a framework of generating adversarial examples for unsupervised models and demonstrate novel applications to data augmentation. Our framework exploits a mutual information neural estimator as an information-theoretic similarity measure to generate adversarial examples without supervision. We propose a new MinMax algorithm with provable convergence guarantees for efficient generation of unsupervised adversarial examples. Our framework can also be extended to supervised adversarial examples. When using unsupervised adversarial examples as a simple plug-in data augmentation tool for model retraining, significant improvements are consistently observed across different unsupervised tasks and datasets, including data reconstruction, representation learning, and contrastive learning. Our results show novel methods and considerable advantages in studying and improving unsupervised machine learning via adversarial examples.