GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
This addresses a challenging gap in time series synthesis for data augmentation, though it appears incremental as it combines known techniques into a unified framework.
The paper tackles the problem of synthesizing both regular and irregular time series data with a single model, presenting GT-GAN, a generative adversarial network that integrates techniques like neural differential equations and achieves superior performance over existing methods.
Time series synthesis is an important research topic in the field of deep learning, which can be used for data augmentation. Time series data types can be broadly classified into regular or irregular. However, there are no existing generative models that show good performance for both types without any model changes. Therefore, we present a general purpose model capable of synthesizing regular and irregular time series data. To our knowledge, we are the first designing a general purpose time series synthesis model, which is one of the most challenging settings for time series synthesis. To this end, we design a generative adversarial network-based method, where many related techniques are carefully integrated into a single framework, ranging from neural ordinary/controlled differential equations to continuous time-flow processes. Our method outperforms all existing methods.