RomanBresson/KAGNN
This is the official repository for our paper KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning.
This project provides the underlying research code for developing and evaluating advanced graph neural networks. It takes structured data represented as graphs and applies sophisticated learning models to classify or predict properties of nodes or entire graphs. Researchers and machine learning engineers working on cutting-edge graph analysis problems would use this.
Use this if you are a researcher or ML engineer interested in exploring or building upon the latest advancements in graph neural networks that incorporate Kolmogorov-Arnold Networks.
Not ideal if you are looking for a pre-packaged solution for a specific graph-based prediction task without needing to delve into model architecture or research.
Stars
53
Forks
6
Language
Python
License
—
Category
Last pushed
Nov 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RomanBresson/KAGNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIAGameWorks/kaolin
A PyTorch Library for Accelerating 3D Deep Learning Research
Jim137/qkan
PyTorch implementation of QKAN "Quantum-inspired Kolmogorov-Arnold Network"...
lgy112112/ikan
ikan: many kan variants for every body
AntonioTepsich/Convolutional-KANs
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN)...
Indoxer/LKAN
Variations of Kolmogorov-Arnold Networks