The official implementation for ICML2024 paper "Learning Divergence Fields for Generalization with Data Geometries"
Related material: [Paper], [Blog]
[2024.05.02] We release the code for the model for three settings: Observed Geometries, Partially Observed Geometries and Unobserved Geometries. More detailed info will be updated soon.
One can download the datasets (Arxiv, Twitch, Cifar, STL, DPPIN) from the google drive link below:
Python 3.8, PyTorch 1.13.0, PyTorch Geometric 2.1.0, NumPy 1.23.4
Please refer to the bash script run.sh in each folder for running the training and evaluation pipeline on different datasets.
If you find our code and model useful, please cite our work. Thank you!