DeepGPT

This repository contains the implementation related to the paper "Deep Prompt Tuning for Graph Transformers". The code is built on top of P-tuning v2 and GraphGPS.

Installation

To get started, follow these steps:

1. Create Conda Environment

Use the provided enviroment file to create Conda environments for the project:

conda env create -f env.yml

2. Activate the Conda Environment

Activate the newly created Conda environment:

conda activate deepgpt

Usage

The running scripts are located in the scripts directory.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If you find this repository useful in your research, please cite the following paper:

@article{2023deepgpt,
  title={Deep Prompt Tuning for Graph Transformers},
  author={Shirkavand, Reza and Huang, Heng},
  journal={arXiv preprint arXiv:2309.10131},
  year={2023}
}