https://github.com/snap-research/largegt
Graph Transformers for Large Graphs
https://github.com/snap-research/largegt
gnn graph-transformer machinelearning transformer
Last synced: 6 months ago
JSON representation
Graph Transformers for Large Graphs
- Host: GitHub
- URL: https://github.com/snap-research/largegt
- Owner: snap-research
- License: other
- Created: 2023-10-04T18:06:24.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-26T22:28:56.000Z (over 1 year ago)
- Last Synced: 2025-03-27T14:22:02.815Z (7 months ago)
- Topics: gnn, graph-transformer, machinelearning, transformer
- Language: Python
- Homepage:
- Size: 132 KB
- Stars: 21
- Watchers: 8
- Forks: 4
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LargeGT: Graph Transformers for Large Graphs
Source code for the paper **[Graph Transformers for Large Graphs](https://arxiv.org/abs/2312.11109)**
>by [Vijay Prakash Dwivedi](http://vijaydwivedi.com.np), [Yozen Liu](https://research.snap.com/team/team-member.html#yozen-liu), [Anh Tuan Luu](https://tuanluu.github.io), [Xavier Bresson](https://scholar.google.com/citations?user=9pSK04MAAAAJ&hl=en), [Neil Shah](https://nshah.net) and [Tong Zhao](https://tzhao.io).
The paper proposes LargeGT which is a scalable Graph Transformer framework designed to efficiently handle large-scale graphs, featuring a combination of fast neighborhood sampling and local-global attention mechanisms.
## 1. Installation
To setup the Python environment with conda, [follow these instructions](./docs/01_installation.md).
## 2. Download data
Download preprocessed data by [running this script](./data/download_data.sh) as:
```
cd data
bash download_data.sh
```
## 3. Run experiments
To run an experiment, run the command:
```
python main.py --dataset --sample_node_len
```
For example:
```
python main.py --dataset ogbn-products --sample_node_len 100
```
To reproduce results, [follow these steps](./docs/03_reproduce.md).
## 4. Acknowledgement
This code repository leverages the open-source codebases released by [GOAT](https://github.com/devnkong/GOAT) and [NAGphormer](https://github.com/JHL-HUST/NAGphormer).
## 5. Reference
:page_with_curl: Paper [on arXiv](https://arxiv.org/abs/2312.11109)
```bibtex
@article{dwivedi2023graph,
title={Graph Transformers for Large Graphs},
author={Dwivedi, Vijay Prakash and Liu, Yozen and Luu, Anh Tuan and Bresson, Xavier and Shah, Neil and Zhao, Tong},
journal={arXiv preprint arXiv:2312.11109},
year={2023}
}
```
## 6. Contact
Please contact vijaypra001@e.ntu.edu.sg for any questions.