Determinate Node Selection for Semi-supervised Classification Oriented Graph Convolutional Networks

TL;DR

This paper introduces a deterministic node selection method called DNS that improves the stability and accuracy of semi-supervised graph convolutional networks by selecting representative nodes based on graph structure.

Contribution

The paper proposes the DNS algorithm for deterministic selection of labeled nodes, enhancing GCN performance and stability in semi-supervised node classification.

Findings

Significant accuracy improvement over baseline methods

Reduction in performance variance across experiments

Effective application across various GCN models

Abstract

Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data. However, the random selection of labeled nodes used by GCNs may lead to unstable generalization performance of GCNs. In this paper, we propose an efficient method for the deterministic selection of labeled nodes: the Determinate Node Selection (DNS) algorithm. The DNS algorithm identifies two categories of representative nodes in the graph: typical nodes and divergent nodes. These labeled nodes are selected by exploring the structure of the graph and determining the ability of the nodes to represent the distribution of data within the graph. The DNS algorithm can be applied quite simply on a wide range of semi-supervised graph neural network models for node classification tasks. Through extensive experimentation, we have demonstrated that the incorporation of the DNS algorithm leads to a remarkable improvement in the average accuracy of the model and a significant decrease in the standard deviation, as compared to the original method.