giannisnik / gnm

Graph Neural Machine: A New Model for Learning with Tabular Data

Graph Neural Machine: A New Model for Learning with Tabular Data

This repository is the official implementation of Graph Neural Machine: A New Model for Learning with Tabular Data.

Requirements

Code is written in Python 3.11 and requires:

• PyTorch 2.1
• Scikit-learn 1.3
• Pandas 2.0

Datasets

The datasets are automatically downloaded when the user executes the script

Training and Evaluation

To train and evaluate the model, 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{nikolentzos2024graph,
  title={Graph Neural Machine: A New Model for Learning with Tabular Data},
  author={Nikolentzos, Giannis and Wang, Siyun and Lutzeyer, Johannes and Vazirgiannis, Michalis},
  journal={arXiv preprint arXiv:2402.02862},
  year={2024}
}