Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/ai4healthuol/sssd

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

https://github.com/ai4healthuol/sssd

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.5%) to scientific vocabulary

Keywords

deep-learning diffusion-models time-series-forecasting time-series-imputation
Last synced: 5 months ago · JSON representation

Repository

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

Basic Info
  • Host: GitHub
  • Owner: AI4HealthUOL
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 875 KB
Statistics
  • Stars: 306
  • Watchers: 8
  • Forks: 54
  • Open Issues: 0
  • Releases: 0
Topics
deep-learning diffusion-models time-series-forecasting time-series-imputation
Created over 3 years ago · Last pushed 9 months ago
Metadata Files
Readme

README.md

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 accepted by TMLR . 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. (here is an example of the feature sampling approach for the datasets with large number of channels )

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

alt text

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

Random Missing

alt text

Missing not at random

alt text

Black-out missing

alt text

Forecast

alt text

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

```bibtex @article{lopezalcaraz2022diffusionbased, title={Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models}, author={Juan Lopez Alcaraz and Nils Strodthoff}, journal={Transactions on Machine Learning Research}, issn={2835-8856}, year={2022}, url={https://openreview.net/forum?id=hHiIbk7ApW}, }

```

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 proposed model code builds on the implementation provided by DiffWave.

Owner

  • Name: AI4HealthUOL
  • Login: AI4HealthUOL
  • Kind: organization
  • Location: Germany

Public repositories of the AI4Health Division at Oldenburg University

GitHub Events

Total
  • Issues event: 6
  • Watch event: 41
  • Issue comment event: 2
  • Push event: 3
  • Fork event: 5
Last Year
  • Issues event: 6
  • Watch event: 41
  • Issue comment event: 2
  • Push event: 3
  • Fork event: 5

Issues and Pull Requests

Last synced: almost 2 years ago

All Time
  • Total issues: 23
  • Total pull requests: 1
  • Average time to close issues: 10 days
  • Average time to close pull requests: about 1 hour
  • Total issue authors: 19
  • Total pull request authors: 1
  • Average comments per issue: 2.39
  • Average comments per pull request: 1.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 15
  • Pull requests: 0
  • Average time to close issues: 15 days
  • Average time to close pull requests: N/A
  • Issue authors: 12
  • Pull request authors: 0
  • Average comments per issue: 2.53
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • YangYu-NUAA (2)
  • Nicholas0917 (2)
  • HarperHao (2)
  • chomgid (2)
  • 666-will (1)
  • abdulfatir (1)
  • betcha-z (1)
  • hawkcl (1)
  • DennisZZQ (1)
  • nick-torenvliet (1)
  • JunSeok94 (1)
  • packer-c (1)
  • fd-guo (1)
  • lzjtd12242002 (1)
  • sw930718 (1)
Pull Request Authors
  • andrewnc (1)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

src/entensions/cauchy/setup.py pypi
src/requirements.txt pypi
  • Babel ==2.9.1
  • Bottleneck ==1.3.5
  • Deprecated ==1.2.13
  • Faker ==17.6.0
  • GitPython ==3.1.30
  • HeapDict ==1.0.1
  • Jinja2 ==3.1.2
  • MAPIE ==0.6.1
  • Markdown ==3.4.1
  • MarkupSafe ==2.1.2
  • Pillow ==9.5.0
  • PyQt5-sip ==12.11.0
  • PySocks ==1.7.1
  • PyWavelets ==1.4.1
  • PyYAML ==6.0
  • Pygments ==2.11.2
  • QtPy ==2.2.0
  • SDF ==0.3.5
  • SciencePlots ==2.0.1
  • Send2Trash ==1.8.0
  • Theano ==1.0.5
  • Werkzeug ==2.2.2
  • absl-py ==1.3.0
  • aiohttp ==3.8.3
  • aiosignal ==1.3.1
  • anyio ==3.5.0
  • appdirs ==1.4.4
  • argon2-cffi ==21.3.0
  • argon2-cffi-bindings ==21.2.0
  • asks ==3.0.0
  • asttokens ==2.0.5
  • astunparse ==1.6.3
  • async-generator ==1.10
  • async-timeout ==4.0.2
  • attrs ==22.1.0
  • audeer ==1.19.0
  • audformat ==0.16.0
  • audinterface ==0.10.2
  • audiofile ==1.1.1
  • audioread ==3.0.0
  • audobject ==0.7.7
  • audresample ==1.1.1
  • backcall ==0.2.0
  • beautifulsoup4 ==4.11.1
  • bidict ==0.22.1
  • biosppy ==1.0.0
  • bleach ==4.1.0
  • brotlipy ==0.7.0
  • cachetools ==5.2.0
  • captum ==0.6.0
  • catalogue ==2.0.8
  • certifi ==2022.12.7
  • cesium ==0.12.1
  • cffi ==1.15.1
  • charset-normalizer ==2.0.4
  • click ==8.1.3
  • cloudpickle ==2.2.1
  • cmake ==3.26.3
  • contourpy ==1.0.7
  • crccheck ==1.3.0
  • cryptography ==38.0.1
  • ctgan ==0.7.1
  • cycler ==0.11.0
  • dask ==2023.1.0
  • data ==0.4
  • datasets ==2.8.0
  • debugpy ==1.5.1
  • decorator ==5.1.1
  • defusedxml ==0.7.1
  • dgl ==0.9.1.post1
  • dill ==0.3.6
  • distributed ==2023.1.0
  • docker-pycreds ==0.4.0
  • docopt ==0.6.2
  • ecg-plot ==0.2.8
  • eeglib ==0.4.1
  • einops ==0.6.0
  • entrypoints ==0.4
  • et-xmlfile ==1.1.0
  • exceptiongroup ==1.1.0
  • executing ==0.8.3
  • fastdtw ==0.3.4
  • fastjsonschema ==2.16.2
  • filelock ==3.6.0
  • fire ==0.4.0
  • flatbuffers ==22.11.23
  • fonttools ==4.25.0
  • frozenlist ==1.3.3
  • fsspec ==2022.11.0
  • funcsigs ==1.0.2
  • future ==0.18.2
  • gast ==0.4.0
  • gatspy ==0.3
  • gitdb ==4.0.10
  • gluonts ==0.11.3
  • google-auth ==2.17.2
  • google-auth-oauthlib ==1.0.0
  • google-pasta ==0.2.0
  • graphviz ==0.20.1
  • grpcio ==1.51.0
  • h11 ==0.14.0
  • h5py ==3.7.0
  • huggingface-hub ==0.10.1
  • idna ==3.4
  • imageio ==2.22.4
  • imbalanced-learn ==0.10.1
  • importlib-metadata ==6.0.0
  • ipykernel ==6.15.2
  • ipython ==8.6.0
  • ipython-genutils ==0.2.0
  • ipywidgets ==7.6.5
  • ishneholterlib ==2020.5.29
  • iso-639 ==0.4.5
  • iso3166 ==2.1.1
  • jax ==0.3.25
  • jedi ==0.18.1
  • jmespath ==1.0.1
  • joblib ==1.2.0
  • json5 ==0.9.6
  • jsonschema ==4.16.0
  • jupyter ==1.0.0
  • jupyter-console ==6.4.3
  • jupyter-server ==1.18.1
  • jupyter_client ==7.3.5
  • jupyter_core ==4.11.2
  • jupyterlab ==3.4.4
  • jupyterlab-pygments ==0.1.2
  • jupyterlab-widgets ==1.0.0
  • jupyterlab_server ==2.15.2
  • keras ==2.11.0
  • keras-nightly ==2.12.0.dev2022120308
  • kiwisolver ==1.4.2
  • latex ==0.7.0
  • libclang ==14.0.6
  • librosa ==0.9.2
  • lightning-utilities ==0.3.0
  • lion-pytorch ==0.0.7
  • lit ==16.0.1
  • llvmlite ==0.39.1
  • locket ==1.0.0
  • lxml ==4.9.1
  • matplotlib ==3.7.1
  • matplotlib-inline ==0.1.6
  • medmnist ==2.2.1
  • mega.py ==1.0.8
  • mistune ==0.8.4
  • mkl-fft ==1.3.1
  • mkl-random ==1.2.2
  • mkl-service ==2.4.0
  • mne ==1.3.0
  • mpmath ==1.3.0
  • msgpack ==1.0.4
  • multidict ==6.0.2
  • multiprocess ==0.70.14
  • multitasking ==0.0.11
  • munkres ==1.1.4
  • nbclassic ==0.4.8
  • nbclient ==0.5.13
  • nbconvert ==6.5.4
  • nbformat ==5.5.0
  • nbstripout ==0.6.1
  • nest-asyncio ==1.5.5
  • networkx ==2.8.8
  • neurokit2 ==0.2.2
  • nimfa ==1.4.0
  • nltk ==3.8.1
  • nmslib ==2.1.1
  • notebook ==6.5.2
  • notebook_shim ==0.2.2
  • numba ==0.56.4
  • numexpr ==2.8.4
  • numpy ==1.23.5
  • oauthlib ==3.2.2
  • object-detection-metrics ==0.4.post1
  • opencv-python ==4.7.0.68
  • openpyxl ==3.1.0
  • opensmile ==2.4.2
  • opt-einsum ==3.3.0
  • outcome ==1.2.0
  • oyaml ==1.0
  • packaging ==23.1
  • pandas ==1.5.1
  • pandocfilters ==1.5.0
  • parso ==0.8.3
  • partd ==1.3.0
  • path ==16.6.0
  • pathlib ==1.0.1
  • pathtools ==0.1.2
  • patsy ==0.5.3
  • pexpect ==4.8.0
  • pickleshare ==0.7.5
  • pip ==22.2.2
  • platformdirs ==3.2.0
  • plotly ==5.13.1
  • ply ==3.11
  • podm ==0.0.19
  • pooch ==1.6.0
  • progressbar2 ==4.2.0
  • prometheus-client ==0.14.1
  • promise ==2.3
  • prompt-toolkit ==3.0.20
  • protobuf ==3.19.6
  • psutil ==5.9.0
  • ptyprocess ==0.7.0
  • pure-eval ==0.2.2
  • pyEDFlib ==0.1.30
  • pyOpenSSL ==22.0.0
  • pyarrow ==10.0.1
  • pyasn1 ==0.4.8
  • pyasn1-modules ==0.2.8
  • pybind11 ==2.10.1
  • pybind11-global ==2.10.1
  • pycocotools ==2.0.6
  • pycorruptor ==0.0.4
  • pycparser ==2.21
  • pycryptodome ==3.16.0
  • pydantic ==1.10.2
  • pyhealth ==1.1.3
  • pyparsing ==3.0.9
  • pypots ==0.0.9
  • pyrsistent ==0.18.0
  • python-dateutil ==2.8.2
  • python-utils ==3.4.5
  • pytorch-lightning ==1.8.2
  • pyts ==0.12.0
  • pytz ==2022.1
  • pyzmq ==23.2.0
  • qtconsole ==5.3.2
  • rdkit ==2022.9.5
  • rdt ==1.3.0
  • regex ==2022.10.31
  • requests ==2.28.1
  • requests-oauthlib ==1.3.1
  • resampy ==0.4.2
  • responses ==0.18.0
  • rsa ==4.9
  • scikit-base ==0.4.5
  • scikit-dimension ==0.3
  • scikit-image ==0.19.3
  • scikit-learn ==1.1.3
  • scikit-multilearn ==0.2.0
  • scikit-plot ==0.3.7
  • scipy ==1.9.3
  • seaborn ==0.12.1
  • sentry-sdk ==1.12.1
  • setproctitle ==1.3.2
  • setuptools ==67.6.1
  • setuptools-scm ==7.1.0
  • shap ==0.41.0
  • shortuuid ==1.0.11
  • shutilwhich ==1.1.0
  • sip ==6.6.2
  • six ==1.16.0
  • sklearn ==0.0.post1
  • sktime ==0.19.0
  • slicer ==0.0.7
  • smmap ==5.0.0
  • sniffio ==1.2.0
  • sortedcontainers ==2.4.0
  • soundfile ==0.11.0
  • soupsieve ==2.3.2.post1
  • srsly ==2.4.5
  • stack-data ==0.2.0
  • statsmodels ==0.13.5
  • stumpy ==1.11.1
  • sympy ==1.11.1
  • tb-nightly ==2.12.0a20221203
  • tblib ==1.7.0
  • tempdir ==0.7.1
  • tenacity ==8.2.2
  • tensorboard ==2.12.1
  • tensorboard-data-server ==0.7.0
  • tensorboard-plugin-wit ==1.8.1
  • tensorflow-addons ==0.19.0
  • tensorflow-estimator ==2.11.0
  • tensorflow-gpu ==2.11.0
  • tensorflow-io-gcs-filesystem ==0.28.0
  • termcolor ==2.1.1
  • terminado ==0.13.1
  • tf-estimator-nightly ==2.12.0.dev2022120309
  • tf-nightly ==2.12.0.dev20221203
  • threadpoolctl ==3.1.0
  • tifffile ==2022.10.10
  • timm ==0.6.12
  • tinycss2 ==1.2.1
  • tokenizers ==0.13.2
  • toml ==0.10.2
  • tomli ==2.0.1
  • toolz ==0.12.0
  • torch ==1.13.0
  • torch-cluster ==1.6.0
  • torch-geometric ==2.2.0
  • torch-scatter ==2.1.0
  • torch-sparse ==0.6.15
  • torchaudio ==0.13.0
  • torchmetrics ==0.10.3
  • torchsummary ==1.5.1
  • torchvision ==0.14.0
  • tornado ==6.2
  • tqdm ==4.65.0
  • traitlets ==5.1.1
  • transformers ==4.25.1
  • trio ==0.22.0
  • tsdb ==0.0.7
  • tsfresh ==0.20.0
  • typeguard ==2.13.3
  • typing_extensions ==4.5.0
  • urllib3 ==1.26.15
  • wandb ==0.13.7
  • wcwidth ==0.2.5
  • webencodings ==0.5.1
  • websocket-client ==0.58.0
  • wfdb ==4.1.0
  • wget ==3.2
  • wheel ==0.40.0
  • widgetsnbextension ==3.5.2
  • wrapt ==1.14.1
  • xgboost ==1.7.4
  • xxhash ==3.2.0
  • yarl ==1.8.1
  • yfinance ==0.1.87
  • zict ==2.2.0
  • zipp ==3.11.0