Two-Stage Aggregation with Dynamic Local Attention for Irregular Time Series

This is a PyTorch implementation of the TADA-Irregular-Time-Series paper:

@article{chen2023dynamic,
  title={Dynamic Local Attention with Hierarchical Patching for Irregular Clinical Time Series},
  author={Chen, Xingyu and Zheng, Xiaochen and Mollaysa, Amina and Sch{\"u}rch, Manuel and Allam, Ahmed and Krauthammer, Michael},
  journal={arXiv preprint arXiv:2311.07744},
  year={2023}
}

This codebase is developed based on the repository available at https://github.com/xingyu617/ml4h_code.