Transferring Social Network Knowledge from Multiple GNN Teachers to Kolmogorov-Arnold Networks

TL;DR

This paper introduces a novel approach that combines multiple GNN teacher models with Kolmogorov-Arnold Networks to improve node classification accuracy and enable efficient graph-free inference.

Contribution

It presents a new framework integrating KANs into GNNs and a multi-teacher knowledge amalgamation method for enhanced performance.

Findings

Improved node classification accuracy on benchmark datasets.

Knowledge amalgamation significantly boosts student model performance.

KAN-based models enable efficient, graph-free inference.

Abstract

Graph Neural Networks (GNNs) have shown strong performance on graph-structured data, but their reliance on graph connectivity often limits scalability and efficiency. Kolmogorov-Arnold Networks (KANs), a recent architecture with learnable univariate functions, offer strong nonlinear expressiveness and efficient inference. In this work, we integrate KANs into three popular GNN architectures-GAT, SGC, and APPNP-resulting in three new models: KGAT, KSGC, and KAPPNP. We further adopt a multi-teacher knowledge amalgamation framework, where knowledge from multiple KAN-based GNNs is distilled into a graph-independent KAN student model. Experiments on benchmark datasets show that the proposed models improve node classification accuracy, and the knowledge amalgamation approach significantly boosts student model performance. Our findings highlight the potential of KANs for enhancing GNN expressiveness and for enabling efficient, graph-free inference.