PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
Paul Jeha, Michael Bohlke-Schneider, Pedro Mercado, Shubham Kapoor, Rajbir Singh Nirwan, Valentin Flunkert, Jan Gasthaus, Tim Januschowski
Abstract
Realistic synthetic time series data of sufficient length enables practical applications in time series modeling tasks, such as forecasting, but remains a challenge. In this paper we present PSA-GAN, a generative adversarial network (GAN) that generates long time series samples of high quality using progressive growing of GANs and self-attention. We show that PSA-GAN can be used to reduce the error in several downstream forecasting tasks over baselines that only use real data. We also introduce a Frechet-Inception Distance-like score for time series, Context-FID, assessing the quality of synthetic time series samples. We find that Context-FID is indicative for downstream performance. Therefore, Context-FID could be a useful tool to develop time series GAN models.
BibTeX
@inproceedings{
jeha2022psagan,
title={{PSA}-{GAN}: Progressive Self Attention {GAN}s for Synthetic Time Series},
author={Paul Jeha and Michael Bohlke-Schneider and Pedro Mercado and Shubham Kapoor and Rajbir Singh Nirwan and Valentin Flunkert and Jan Gasthaus and Tim Januschowski},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=Ix_mh42xq5w}
}