andrewnc / SSSD

Repository for the paper: 'Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models'

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

This is the official repository for the paper Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models. In combination with (conditional) diffusion and state-space models, we put forward diverse algorithms, particualary, we propose the generative model $SSSD^{S4}$, which is suited to capture long-term dependencies and demonstrates state-of-the-art results in time series across diverse missing scenarios and datasets.

Datasets and experiments

Visit the source directory to get datasets download and experiments reproducibility instructions.

Our proposed $SSSD^{S4}$ model architecture:

$SSSD^{S4}$ robustness on diverse scenarios:

Random Missing

Missing not at random

Black-out missing

Forecast

Please cite our publication if you found our research to be helpful.

@misc{https://doi.org/10.48550/arxiv.2208.09399,
  doi = {10.48550/ARXIV.2208.09399},
  url = {https://arxiv.org/abs/2208.09399},
  author = {Alcaraz, Juan Miguel Lopez and Strodthoff, Nils},
  keywords = {Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

Acknowledgments

We would like thank the authors of the the S4 model for releasing and maintaining the source code for Structured State Space Models. Similarly, our $SSSD^{S4}$ code builds on the implementation provided by DiffWave.