paper-with-me

홈 › Papers

Towards Controllable Time Series Generation

2024-03-06 · Yifan Bao, Yihao Ang, Qiang Huang, Anthony K. H. Tung, Zhiyong Huang

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 \textbf{C}ontrollable \textbf{T}ime \textbf{S}eries (\textsf{CTS}), an innovative VAE-agnostic framework tailored for CTSG. A key feature of \textsf{CTS} 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 \textsf{CTS}'s exceptional capabilities in generating high-quality, controllable outputs. This underscores its adeptness in seamlessly integrating latent features with external conditions. Extending \textsf{CTS} to the image domain highlights its remarkable potential for explainability and further reinforces its versatility across different modalities.

📄 PDF Abstract BibTeX arXiv:2403.03698

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Generation

Similar Papers 제목 키워드 기반

GRATIS: GeneRAting TIme Series with diverse and controllable characteristics

2019-03-07 · Yanfei Kang, Rob J. Hyndman, Feng Li

The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks. The evaluation of these new methods requires eith…

BenchmarkingClusteringDiversityGeneral Classification+4

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

2026-05-02 · Seokhyun Lee, Jaeho Kim, Changjun Oh, Mihaela van der Schaar 외 arxiv

Time-series generative models often lack control over temporal granularity, forcing users to accept whatever granularity the model produces. To enable truly user-driven generation, we introduce TimeTok, a unified framewo…

Unsupervised and Interpretable Synthesizing for Electrical Time Series Based on Information Maximizing Generative Adversarial Nets

2024-07-18 · Zhenghao Zhou, Yiyan Li, Runlong Liu, Zheng Yan 외

Generating synthetic data has become a popular alternative solution to deal with the difficulties in accessing and sharing field measurement data in power systems. However, to make the generation results controllable, ex…

DescriptiveSynthetic Data GenerationTime Series

Less Is More: Generating Time Series with LLaMA-Style Autoregression in Simple Factorized Latent Spaces

2025-11-07 · Siyuan Li, Yifan Sun, Lei Cheng, Lewen Wang 외 arxiv

Generative models for multivariate time series are essential for data augmentation, simulation, and privacy preservation, yet current state-of-the-art diffusion-based approaches are slow and limited to fixed-length windo…

Data Augmentation

CoFinDiff: Controllable Financial Diffusion Model for Time Series Generation

2025-03-06 · Yuki Tanaka, Ryuji Hashimoto, Takehiro Takayanagi, Zhe Piao 외

The generation of synthetic financial data is a critical technology in the financial domain, addressing challenges posed by limited data availability. Traditionally, statistical models have been employed to generate synt…

DiversitySynthetic Data GenerationTime SeriesTime Series Generation