Research on the application of graph data structure and graph neural network in node classification/clustering tasks

TL;DR

This paper analyzes graph data structures and neural networks, demonstrating that GNNs significantly outperform traditional algorithms in node classification and clustering, and explores integration strategies for improved graph learning.

Contribution

It provides a comprehensive theoretical analysis, comparative evaluation, and integration strategies for classical algorithms and GNNs in graph-based tasks.

Findings

GNNs improve accuracy by 43% to 70% over traditional methods.

Comparative experiments validate the effectiveness of GNNs in node classification and clustering.

Theoretical guidance for integrating classical algorithms with GNNs is proposed.

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.