الملخص
Synthetic time series are increasingly used for data augmentation, privacy-preserving data sharing, and downstream model development, yet faithfully reproducing both multi-scale temporal structure and cross-channel dependencies remains challenging. We study multivariate time-series generation through flow matching in the wavelet domain. By operating on multilevel discrete wavelet coefficients rather than directly in the time domain, the model represents coarse structure and progressively finer details at separate scales. Their naturally different variances further induce an implicit coarse-to-fine generative process without requiring an explicit multi-scale schedule. Since the transform acts independently on each channel, we pair it with a channel-token transformer whose attention directly models cross-channel dependencies. Across seven benchmark datasets and four sequence lengths, our method is best or tied on a majority of dataset-metric combinations, with the largest and most consistent improvements in Context-FID and discriminative score.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Poinsignon, L., Goncalves, J. D. S., Ruiperez-Campillo, S., & Vogt, J. E. (2026). Wavelet Flow Matching for Time Series. https://omanscience.com/ar/articles/wavelet-flow-matching-for-time-series
MLA 9
Poinsignon, Lucas, et al. "Wavelet Flow Matching for Time Series." https://omanscience.com/ar/articles/wavelet-flow-matching-for-time-series.
شيكاغو (المؤلف–التاريخ)
Poinsignon, Lucas, Jorge da Silva Goncalves, Samuel Ruiperez-Campillo, and Julia E. Vogt. 2026. "Wavelet Flow Matching for Time Series." https://omanscience.com/ar/articles/wavelet-flow-matching-for-time-series.
هارفارد
Poinsignon, L., Goncalves, J. D. S., Ruiperez-Campillo, S. and Vogt, J. E. (2026) 'Wavelet Flow Matching for Time Series', Available at: https://omanscience.com/ar/articles/wavelet-flow-matching-for-time-series.
فانكوفر
Poinsignon L, Goncalves JDS, Ruiperez-Campillo S, Vogt JE. Wavelet Flow Matching for Time Series. https://omanscience.com/ar/articles/wavelet-flow-matching-for-time-series
IEEE
L. Poinsignon, J. D. S. Goncalves, S. Ruiperez-Campillo, and J. E. Vogt, "Wavelet Flow Matching for Time Series," https://omanscience.com/ar/articles/wavelet-flow-matching-for-time-series.