Diffusion-TS: Interpretable Diffusion for General Time Series Generation

arXiv:2403.01742v1 Announce Type: new
Abstract: Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and forecasting. In this paper, we propose Diffusion-TS, a novel diffusion-based framework that generates multivariate time series samples of high quality by using an encoder-decoder transformer with disentangled temporal representations, in which the decomposition technique guides Diffusion-TS to capture the semantic meaning of time series while transformers mine detailed sequential information …

abstract arxiv audio audio synthesis cs.ai cs.lg denoising diffusion forecasting framework general generative generative models imputation multivariate novel paper paradigm quality samples series synthesis time series type