GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks

Fan Zhang, Xin Zhang

6/19/2024

cs.LGcs.AI

Official code: Ryanfzhang/GraphKan (70 stars, last commit 2024-06-04).

Abstract

Massive number of applications involve data with underlying relationships embedded in non-Euclidean space. Graph neural networks (GNNs) are utilized to extract features by capturing the dependencies within graphs. Despite groundbreaking performances, we argue that Multi-layer perceptrons (MLPs) and fixed activation functions impede the feature extraction due to information loss. Inspired by Kolmogorov Arnold Networks (KANs), we make the first attempt to GNNs with KANs. We discard MLPs and activation functions, and instead used KANs for feature extraction. Experiments demonstrate the effectiveness of GraphKAN, emphasizing the potential of KANs as a powerful tool. Code is available at https://github.com/Ryanfzhang/GraphKan.

View on arXiv View PDF

Code Implementations(1)

Ryanfzhang/GraphKanOfficial100%

Implementation of GraphKan with torch geometrics and its application on signal classification

7018PythonMay 29, 20242 years ago

Similar Papers

GKAN: Graph Kolmogorov-Arnold Networks

90% match2024

Kolmogorov-Arnold Graph Neural Networks

88% match2024

KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning

88% match1 repo602024

KAN: Kolmogorov-Arnold Networks

86% match1 repo16.3k2024

KAN: Kolmogorov-Arnold Networks

86% match3 repos16.3k2026

Kolmogorov-Arnold Network Autoencoders

85% match3 repos62024

Cite this paper

@article{zhang2024graphkan,
  title  = {GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks},
  author = {Fan Zhang and Xin Zhang},
  year   = {2024},
  eprint = {2406.13597},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.13597v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/2406.13597.svg)](https://codeofpaper.com/paper/2406.13597)