TSGM: Regular and Irregular Time-series Generation using Score-based Generative Models
This work addresses time-series synthesis for applications requiring realistic data generation, but it is incremental as it adapts an existing method to a new domain.
The authors tackled the problem of generating both regular and irregular time-series data by applying score-based generative models, achieving state-of-the-art sampling diversity and quality on various datasets.
Score-based generative models (SGMs) have demonstrated unparalleled sampling quality and diversity in numerous fields, such as image generation, voice synthesis, and tabular data synthesis, etc. Inspired by those outstanding results, we apply SGMs to synthesize time-series by learning its conditional score function. To this end, we present a conditional score network for time-series synthesis, deriving a denoising score matching loss tailored for our purposes. In particular, our presented denoising score matching loss is the conditional denoising score matching loss for time-series synthesis. In addition, our framework is such flexible that both regular and irregular time-series can be synthesized with minimal changes to our model design. Finally, we obtain exceptional synthesis performance on various time-series datasets, achieving state-of-the-art sampling diversity and quality.