/pi-GNN

Permute Me Softly: Learning Soft Permutations for Graph Representations

Primary LanguagePython

Permute Me Softly: Learning Soft Permutations for Graph Representations

Code for the paper Permute Me Softly: Learning Soft Permutations for Graph Representations.

Requirements

Code is written in Python 3.7 and requires:

  • PyTorch 1.9
  • PyTorch Geometric 2.0
  • NetworkX 2.2

Run the model

You can specify the dataset and the hyperparameters in the main.py file, and then execute:

python main.py

Cite

Please cite our paper if you use this code:

@article{nikolentzos2023permute,
  title={Permute me softly: learning soft permutations for graph representations},
  author={Nikolentzos, Giannis and Dasoulas, George and Vazirgiannis, Michalis},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={45},
  number={4},
  pages={5087--5098},
  year={2023},
  publisher={IEEE}
}

Provided for academic use only