Research on the application of graph data structure and graph neural network in node classification/clustering tasks
This work addresses the challenge of analyzing non-Euclidean graph data for applications like social and biological networks, but it is incremental as it focuses on comparative evaluation and integration strategies.
The study tackled node classification and clustering tasks on graph-structured data by comparing traditional algorithms with Graph Neural Networks (GNNs), finding that GNNs achieved accuracy improvements of 43% to 70% over traditional methods.
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.