🤖 AI Summary
Traditional methods for node classification and clustering on graph-structured data—such as social and biological networks—are limited by their inability to effectively model non-Euclidean geometric properties inherent in graphs. To address this, we propose a synergistic modeling framework that integrates classical graph algorithms with graph neural networks (GNNs). Our approach systematically analyzes the representational disparities between these two paradigms and constructs an interpretable graph representation learning scheme, thereby providing theoretical foundations for non-Euclidean structural modeling. Extensive experiments on multiple benchmark graph datasets demonstrate that the proposed method achieves 43%–70% higher accuracy in both node classification and clustering compared to standalone classical algorithms (e.g., Label Propagation, Spectral Clustering) and baseline GNN models. These results robustly validate the dual advantages of our fusion strategy—superior accuracy and enhanced robustness—over existing approaches.
📝 Abstract
Graph-structured data are pervasive across domains including social networks, biological networks, and knowledge graphs. Due to their non-Euclidean nature, such data pose significant challenges to conventional machine learning methods. This study investigates graph data structures, classical graph algorithms, and Graph Neural Networks (GNNs), providing comprehensive theoretical analysis and comparative evaluation. Through comparative experiments, we quantitatively assess performance differences between traditional algorithms and GNNs in node classification and clustering tasks. Results show GNNs achieve substantial accuracy improvements of 43% to 70% over traditional methods. We further explore integration strategies between classical algorithms and GNN architectures, providing theoretical guidance for advancing graph representation learning research.