Autoencoders and Generative Adversarial Networks for Imbalanced Sequence Classification

Stephanie Ger, Diego Klabjan

Keywords: imbalanced multivariate time series classification

TL;DR: We introduce a novel oversampling method for variable length, multivariate time series data that significantly improves classification accuracy.

Abstract: We introduce a novel synthetic oversampling method for variable length, multi- feature sequence datasets based on autoencoders and generative adversarial net- works. We show that this method improves classification accuracy for highly imbalanced sequence classification tasks. We show that this method outperforms standard oversampling techniques that use techniques such as SMOTE and autoencoders. We also use generative adversarial networks on the majority class as an outlier detection method for novelty detection, with limited classification improvement. We show that the use of generative adversarial network based synthetic data improves classification model performance on a variety of sequence data sets.