KAN4Graph

October 14, 2024 ยท View on GitHub

Implementation of Kolmogorov-Arnold Network (KAN) for Graphs. Any communications, collaborations, issues, PRs are welcomed. The contributors will be listed here. Please contact yueliu19990731@163.com. If you find this repository useful to your research or work, it is really appreciate to star this repository. :heart:

stars forks  issues  visitors

Table of Contents
  1. Usage
  2. Acknowledgement

Usage

Requirements

KAN4Graph is implemented with Python3.8.16 and 1 NVIDIA Tesla V100 SXM2 16 GB

Python package information is summarized in requirements.txt:

  • torch==1.7.1
  • tqdm==4.59.0
  • numpy==1.19.2
  • munkres==1.1.4
  • scikit_learn==1.2.0

Datasets

DatasetType# Nodes# Feature Dimensions# Edges# Classes
BATAttribute Graph1318110384
UATAttribute Graph1,19023913,5994
EATAttribute Graph3992035,9944

still updating...

Quick Start

clone this repository and change directory to KAN4Graph

git clone https://github.com/yueliu1999/KAN4Graph.git
cd ./KAN4Graph

run codes

python train.py

Results

DatasetMetricScore
BATACC77.86
NMI54.48
ARI52.33
F177.34
UATACC57.05
NMI25.49
ARI24.97
F155.80
EATACC57.87
NMI34.16
ARI27.52
F158.09

still updating...

Acknowledgements

Our code are partly based on the following GitHub repository. Thanks for their awesome works.

  • pykan: the official implement of KAN.
  • fast-kan: the implement of KAN (fast version).
  • Awesome Deep Graph Clustering: a collection of deep graph clustering (papers, codes, and datasets).
  • SCGC: the official implement of Simple Contrastive Graph Clustering (SCGC) model.

Contributors

yueliu1999

If you find this repository helpful, please cite our paper.

@article{liuyue_SCGC,
  title={Simple contrastive graph clustering},
  author={Liu, Yue and Yang, Xihong and Zhou, Sihang and Liu, Xinwang},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2023},
  publisher={IEEE}
}

@misc{KAN4Graph,
  author = {Yue Liu},
  title = {KAN4Graph},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/yueliu1999/KAN4Graph}},
}

(back to top)