Diffusion-Based Time Series Imputation and Forecasting with Structured State Space Models

Abstract

The imputation of missing values represents a significant obstacle for many real-world data analysis pipelines. Here, we focus on time series data and put forward SSSD, an imputation model that relies on two emerging technologies, (conditional) diffusion models as state-ofthe-art generative models and structured state space models as internal model architecture, which are particularly suited to capture long-term dependencies in time series data. We demonstrate that SSSD matches or even exceeds state-of-the-art probabilistic imputation and forecasting performance on a broad range of data sets and different missingness scenarios, including the challenging blackout-missing scenarios, where prior approaches failed to provide meaningful results.

Cite

Text

Alcaraz and Strodthoff. "Diffusion-Based Time Series Imputation and Forecasting with Structured State Space Models." Transactions on Machine Learning Research, 2023.

Markdown

[Alcaraz and Strodthoff. "Diffusion-Based Time Series Imputation and Forecasting with Structured State Space Models." Transactions on Machine Learning Research, 2023.](https://mlanthology.org/tmlr/2023/alcaraz2023tmlr-diffusionbased/)

BibTeX

@article{alcaraz2023tmlr-diffusionbased,
  title     = {{Diffusion-Based Time Series Imputation and Forecasting with Structured State Space Models}},
  author    = {Alcaraz, Juan Lopez and Strodthoff, Nils},
  journal   = {Transactions on Machine Learning Research},
  year      = {2023},
  url       = {https://mlanthology.org/tmlr/2023/alcaraz2023tmlr-diffusionbased/}
}