2024/03/06 by Yifan Bao, Bao, Yifan, Yihao Ang +7 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Databases (cs.DB) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Time Series Analysis and Forecasting
paper · pdf · doi:10.48550/arxiv.2403.03698
openalex publication_date 2024/03/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Time Series Generation (TSG) has emerged as a pivotal technique in synthesizing data that accurately mirrors real-world time series, becoming indispensable in numerous applications. Despite significant advancements in TSG, its efficacy frequently hinges on having large training datasets. This dependency presents a substantial challenge in data-scarce scenarios, especially when dealing with rare or unique conditions. To confront these challenges, we explore a new problem of Controllable Time Series Generation (CTSG), aiming to produce synthetic time series that can adapt to various external conditions, thereby tackling the data scarcity issue. In this paper, we propose Controllable Time Series (\textsfCTS), an innovative VAE-agnostic framework tailored for CTSG. A key feature of \textsfCTS is that it decouples the mapping process from standard VAE training, enabling precise learning of a complex interplay between latent features and external conditions. Moreover, we develop a comprehensive evaluation scheme for CTSG. Extensive experiments across three real-world time series datasets showcase \textsfCTS's exceptional capabilities in generating high-quality, controllable outputs. This underscores its adeptness in seamlessly integrating latent features with external conditions. Extending \textsfCTS to the image domain highlights its remarkable potential for explainability and further reinforces its versatility across different modalities.