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

2025/08/08 by Yuan-Hung Chao, Chao, Yuan-Hung, Chia-Hsun Lu +3
Computer Science · #Advanced Graph Neural Networks #Artificial neural network #Benchmark (surveying) #FOS: Computer and information sciences #Graph #Graph Theory and Algorithms #Knowledge graph #Machine Learning (cs.LG) #Machine Learning in Healthcare #Node (physics) #Scalability

paper · pdf · doi:10.48550/arxiv.2508.06663

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/08/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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.

Citations

• KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning
• Kolmogorov-Arnold Graph Neural Networks
• GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks
• GKAN: Graph Kolmogorov-Arnold Networks
• KAN: Kolmogorov-Arnold Networks
• Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
• Knowledge Distillation: A Survey
• Distilling Knowledge from Graph Convolutional Networks
• Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
• Simplifying Graph Convolutional Networks
• Graph Neural Networks: A Review of Methods and Applications
• Graph neural networks: A review of methods and applications
• Pitfalls of Graph Neural Network Evaluation
• Amalgamating Knowledge towards Comprehensive Classification
• Graph Attention Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Distilling the Knowledge in a Neural Network

Related

• GKAN: Graph Kolmogorov-Arnold Networks
• KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning
• Kolmogorov-Arnold Graph Neural Networks
• Enhancing Graph Neural Networks: A Mutual Learning Approach
• KA-GNN: Kolmogorov-Arnold Graph Neural Networks for Molecular Property Prediction