Data Augmentation Using GANs
Preprint
Abstract
In this paper we propose the use of Generative Adversarial Networks (GAN) to generate artificial training data for machine learning tasks. The generation of artificial training data can be extremely useful in situations such as imbalanced data sets, performing a role similar to SMOTE or ADASYN. It is also useful when the data contains sensitive information, and it is desirable to avoid using the original data set as much as possible (example: medical data). We test our proposal on benchmark data sets using different network architectures, and show that a Decision Tree (DT) classifier trained using the training data generated by the GAN reached the same, (and surprisingly sometimes better), accuracy and recall than a DT trained on the original data set.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning StrategyIEEE Transactions on Neural Networks and Learning Systems, 2017
- The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncologyOncotarget, 2016
- A Novel Boundary Oversampling Algorithm Based on Neighborhood Rough Set Model: NRSBoundary-SMOTEMathematical Problems in Engineering, 2013
- SMOTE: Synthetic Minority Over-sampling TechniqueJournal of Artificial Intelligence Research, 2002