KAN KAN Buff Signed Graph Neural Networks?

TL;DR

This paper introduces KAN-enhanced Signed Graph Convolutional Networks (KASGCN), which integrate Kolmogorov-Arnold Neural Networks into signed graph analysis, showing competitive performance in community detection and link sign prediction tasks.

Contribution

The paper proposes a novel integration of KAN into SGCNs, enhancing signed graph embeddings and analysis capabilities with promising results.

Findings

KASGCN performs comparably to standard SGCNs on key tasks.

Performance varies with graph characteristics and parameter choices.

KASGCN shows potential for improved signed graph analysis.

Abstract

Graph Representation Learning aims to create effective embeddings for nodes and edges that encapsulate their features and relationships. Graph Neural Networks (GNNs) leverage neural networks to model complex graph structures. Recently, the Kolmogorov-Arnold Neural Network (KAN) has emerged as a promising alternative to the traditional Multilayer Perceptron (MLP), offering improved accuracy and interpretability with fewer parameters. In this paper, we propose the integration of KANs into Signed Graph Convolutional Networks (SGCNs), leading to the development of KAN-enhanced SGCNs (KASGCN). We evaluate KASGCN on tasks such as signed community detection and link sign prediction to improve embedding quality in signed networks. Our experimental results indicate that KASGCN exhibits competitive or comparable performance to standard SGCNs across the tasks evaluated, with performance variability depending on the specific characteristics of the signed graph and the choice of parameter settings. These findings suggest that KASGCNs hold promise for enhancing signed graph analysis with context-dependent effectiveness.