Balancing Imbalanced Datasets Using Generative Adversarial Neural Networks

Balancing Imbalanced Datasets Using Generative Adversarial Neural Networks

연구 분야: Artificial Intelligence

학회: 2021 29th Telecommunications Forum (TELFOR)

In this paper, the problem of balancing machine learning datasets and its potential solution using generative adversarial networks is presented. Several training methods and models in generating minority class samples were examined using two well-known datasets: MNIST and CIFAR10. In order to achieve data imbalance, a percentage of samples was artificially removed from one class in both datasets. Generative adversarial network is initialized with the parameters of the autoencoder trained over the same dataset. Generated noise is limited based on the distribution of the latent space of the autoencoder. Three methods of generative adversarial network training which provide class label context to the network were examined. Two methods gave satisfactory results for the problem of generating samples from the MNIST dataset, while the method of duplicating labels proved unsatisfactory.