GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks

TL;DR

This paper introduces GT-GAN, a versatile generative adversarial network capable of synthesizing both regular and irregular time series data without modifications, advancing data augmentation techniques in deep learning.

Contribution

The paper presents the first general purpose time series synthesis model using GANs that handles both regular and irregular data types without changes.

Findings

Outperforms existing time series synthesis methods

Effective for both regular and irregular data

Integrates advanced neural differential equations and continuous time-flow processes

Abstract

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.