Score: 3

TSGM: Regular and Irregular Time-series Generation using Score-based Generative Models

Published: November 26, 2025 | arXiv ID: 2511.21335v1

By: Haksoo Lim , Jaehoon Lee , Sewon Park and more

BigTech Affiliations: Samsung

Potential Business Impact:

Creates realistic fake time data for any use.

Business Areas:
Simulation Software

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.

Country of Origin
🇰🇷 South Korea, Korea, Republic of

Page Count
15 pages

Category
Computer Science:
Machine Learning (CS)