PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer

This repository contains the PyTorch implementation of our paper "PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer" published in KDD 2024.

📋 Environment Setup

Ensure you have the following dependencies installed:

• PyTorch: 2.0.0
• Torch Geometric: 2.3.0

🗂️ Code Structure

• Node Classification: Contains the code for the main results presented in Table 5 of the paper.
• Node Classification on Large Graphs: Contains the code for the results shown in Table 6.

📝 Citation

If you find this work useful in your research, please consider citing it:

@inproceedings{10.1145/3637528.3671849,
author = {Ma, Jiahong and He, Mingguo and Wei, Zhewei},
title = {PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer},
year = {2024},
isbn = {9798400704901},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3637528.3671849},
doi = {10.1145/3637528.3671849},
booktitle = {Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages = {2118–2129},
numpages = {12},
keywords = {graph filter, graph neural network, graph transformer},
location = {Barcelona, Spain},
series = {KDD '24}
}

📬 Contact

If you have any questions, please feel free to contact me at [email protected]