(Architecture of a naive GCN versus that of PE-GNN, enhanced with a positional encoder.)
This is the official repository for the paper Positional Encoder Graph Neural Networks for Geographic Data (Konstantin Klemmer, Nathan Safir, Daniel B. Neill).
The source code for PE-GNN (using PyTorch
) can be found in the src
folder. Its built on PyTorch Geometric (ICLR-W, 2019) and Space2Vec (ICLR, 2020).
We also provide an interactive example notebook to test PE-GNN via Google Colab
If you want to cite our work, you can use the following reference:
@misc{klemmer2021positional,
title={Positional Encoder Graph Neural Networks for Geographic Data},
author={Konstantin Klemmer and Nathan Safir and Daniel B Neill},
year={2021},
eprint={2111.10144},
archivePrefix={arXiv},
primaryClass={cs.LG}
}