Add the model CDSA - Githubissues

WenjieDu / PyPOTS

A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neural network models for scientific analysis tasks of imputation/classification/clustering/forecasting/anomaly detection/cleaning on incomplete industrial (irregularly-sampled) multivariate TS with NaN missing values

https://pypots.com

BSD 3-Clause "New" or "Revised" License

1.04k stars 99 forks source link

Add the model CDSA #218

Open wx0chan opened 1 year ago

wx0chan commented 1 year ago

1. Model description

CDSA: cross-dimensional self-attention https://arxiv.org/abs/1905.09904

2. Check open-source status

[ ] The model implementation is publicly available

3. Provide useful information for the implementation

Reproduced with reference to the original paper.

WenjieDu commented 1 year ago

Hi there 👋,

Thank you so much for your attention to PyPOTS! You can follow me on GitHub to receive the latest news of PyPOTS. If you find PyPOTS helpful to your work, please star⭐️ this repository. Your star is your recognition, which can help more people notice PyPOTS and grow PyPOTS community. It matters and is definitely a kind of contribution to the community.

I have received your message and will respond ASAP. Thank you for your patience! 😃

Best, Wenjie

WenjieDu commented 8 months ago

The official code repo with incomplete implementation in TF https://github.com/ICLR-Submission/cross-dimensional-attention (according to the info on the submission page https://openreview.net/forum?id=SJxRKT4Fwr)

An unofficial implementation in TF https://github.com/Gabriel-Macias/cdsa_imputation