ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs
If you like our project, please give us a star ⭐ on GitHub for the latest update.
![](https://img.shields.io/badge/DSAIL%40HKUST-8A2BE2) ![GitHub stars](https://img.shields.io/github/stars/NineAbyss/ZeroG.svg) ![](https://img.shields.io/badge/license-MIT-blue)
This is the official implementation of the following paper:
> **ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs** [[Paper](https://arxiv.org/abs/2402.11235)]
>
> Yuhan Li, Peisong Wang, Zhixun Li, Jeffrey Xu Yu, Jia Li
![](https://github.com/NineAbyss/ZeroG/raw/main/ZeroG.png)
The framework of ZeroG.
# Environment Setup
Before you begin, ensure that you have Anaconda or Miniconda installed on your system. This guide assumes that you have a CUDA-enabled GPU.
After create your conda environment (we recommend python==3.10), please run
```
pip install -r requirements.txt
```
to install python packages.
# Datasets
Datasets ```tech.pt``` and ```home.pt``` are availabel in this [link](https://drive.google.com/drive/folders/1kifRUaZ9JzcjByj47FeANfXEeEZd4sJk), while other datasets in ZeroG are available in this [link](https://drive.google.com/drive/folders/1WfBIPA3dMd8qQZ6QlQRg9MIFGMwnPdFj?usp=drive_link).
Please download and place them in folder ```datasets```.
# Run ZeroG
```
bash run.sh
```
**📑 If you find our projects helpful to your research, please consider citing:**
```
@article{li2024zerog,
title={ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs},
author={Li, Yuhan and Wang, Peisong and Li, Zhixun and Yu, Jeffrey Xu and Li, Jia},
journal={arXiv preprint arXiv:2402.11235},
year={2024}
}
```
## FYI: our other works
🔥 A Survey of Graph Meets Large Language Model: Progress and Future Directions (IJCAI'24) ![GitHub stars](https://img.shields.io/github/stars/yhLeeee/Awesome-LLMs-in-Graph-tasks.svg)
Github Repo | Paper