# NAGphormer

**Repository Path**: jdlc105/NAGphormer

## Basic Information

- **Project Name**: NAGphormer
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-08-14
- **Last Updated**: 2024-08-14

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# NAGphormer
This is the code for our ICLR 2023 paper 
**NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs**.

![NAGphormer](./NAGphormer.jpg)

## Requirements
Python == 3.8

Pytorch == 1.11

dgl == 0.9

CUDA == 10.2


## Usage

You can run each command in "commands.txt".

You could change the hyper-parameters of NAGphormer if necessary.

Due to the space limitation, we only provide several small datasets in the "dataset" folder.

For small-scale datasets, you can download them from https://docs.dgl.ai/tutorials/blitz/index.html.

For large-scale datasets, you can download them from https://github.com/wzfhaha/GRAND-plus.



## Cite
If you find this code useful, please consider citing the original work by authors:
```
@inproceedings{chennagphormer,
  title={NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs},
  author={Chen, Jinsong and Gao, Kaiyuan and Li, Gaichao and He, Kun},
  booktitle={Proceedings of the International Conference on Learning Representations},
  year={2023}
}
```