Skip to content

Latest commit

 

History

History
44 lines (30 loc) · 827 Bytes

readme.md

File metadata and controls

44 lines (30 loc) · 827 Bytes

Implmentation code for "Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning" accepted by AISTATS2024

The architecture of the proposed KCP model

Requirements:

numpy==1.23.3
pandas==1.4.4
PyYAML==6.0
scikit_learn==1.1.3
torch==1.9.1
torch_geometric==2.1.0.post1

Usage

  • Choose the dataset from config yaml

  • Pretraining:

    python trains.py
  • Downstream finetuing and evaluation:

    python models/ds_model_2stage.py

Citation

@article{li2024non,
  title={Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning},
  author={Li, Zhishuai and Nie, Yunhao and Li, Ziyue and Bai, Lei and Lv, Yisheng and Zhao, Rui},
  journal={arXiv preprint arXiv:2401.12681},
  year={2024}
}