Kolmogorov-Arnold Graph Neural Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: De Carlo, Gianluca, Mastropietro, Andrea, Anagnostopoulos, Aris
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908385709916160
author De Carlo, Gianluca
Mastropietro, Andrea
Anagnostopoulos, Aris
author_facet De Carlo, Gianluca
Mastropietro, Andrea
Anagnostopoulos, Aris
contents Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN's design inherently provides clear insights into the model's decision-making process, eliminating the need for post-hoc explainability techniques. This paper discusses the methodology, performance, and interpretability of GKAN, highlighting its potential for applications in domains where interpretability is crucial.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Kolmogorov-Arnold Graph Neural Networks
De Carlo, Gianluca
Mastropietro, Andrea
Anagnostopoulos, Aris
Machine Learning
Artificial Intelligence
Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN's design inherently provides clear insights into the model's decision-making process, eliminating the need for post-hoc explainability techniques. This paper discusses the methodology, performance, and interpretability of GKAN, highlighting its potential for applications in domains where interpretability is crucial.
title Kolmogorov-Arnold Graph Neural Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.18354