PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
This work addresses the problem of generating high-quality synthetic time series for applications like forecasting, offering a potentially useful tool for developers, but it appears incremental as it builds on existing GAN techniques.
The paper tackles the challenge of generating realistic long synthetic time series data by introducing PSA-GAN, which uses progressive growing and self-attention, and shows it reduces error in downstream forecasting tasks over baselines using only real data. It also proposes Context-FID, a new metric for assessing synthetic time series quality, finding that lower scores correlate with better model performance.
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 two downstream forecasting tasks over baselines that only use real data. We also introduce a Frechet-Inception Distance-like score, Context-FID, assessing the quality of synthetic time series samples. In our downstream tasks, we find that the lowest scoring models correspond to the best-performing ones. Therefore, Context-FID could be a useful tool to develop time series GAN models.