StyleTime: Style Transfer for Synthetic Time Series Generation

TL;DR

StyleTime introduces a novel method for time series style transfer that combines content and style for synthetic data generation, improving forecasting models through data augmentation.

Contribution

The paper proposes a new formulation and algorithm for time series style transfer, extending style transfer concepts from images to one-dimensional data.

Findings

Stylized synthetic data enhances RNN forecasting performance

StyleTime outperforms existing time series generation methods

Evaluation metrics demonstrate improved realism of stylized data

Abstract

Neural style transfer is a powerful computer vision technique that can incorporate the artistic "style" of one image to the "content" of another. The underlying theory behind the approach relies on the assumption that the style of an image is represented by the Gram matrix of its features, which is typically extracted from pre-trained convolutional neural networks (e.g., VGG-19). This idea does not straightforwardly extend to time series stylization since notions of style for two-dimensional images are not analogous to notions of style for one-dimensional time series. In this work, a novel formulation of time series style transfer is proposed for the purpose of synthetic data generation and enhancement. We introduce the concept of stylized features for time series, which is directly related to the time series realism properties, and propose a novel stylization algorithm, called StyleTime, that uses explicit feature extraction techniques to combine the underlying content (trend) of one time series with the style (distributional properties) of another. Further, we discuss evaluation metrics, and compare our work to existing state-of-the-art time series generation and augmentation schemes. To validate the effectiveness of our methods, we use stylized synthetic data as a means for data augmentation to improve the performance of recurrent neural network models on several forecasting tasks.