Graph Similarity Regularized Softmax for Semi-Supervised Node Classification
This is an incremental improvement for researchers in graph machine learning, addressing the lack of spatial information in softmax classifiers for node classification tasks.
The paper tackled the problem of semi-supervised node classification in graph neural networks by proposing a graph similarity regularized softmax to incorporate spatial graph information, resulting in good performance and generalization on assortative and disassortative graphs.
Graph Neural Networks (GNNs) are powerful deep learning models designed for graph-structured data, demonstrating effectiveness across a wide range of applications.The softmax function is the most commonly used classifier for semi-supervised node classification. However, the softmax function lacks spatial information of the graph structure. In this paper, we propose a graph similarity regularized softmax for GNNs in semi-supervised node classification. By incorporating non-local total variation (TV) regularization into the softmax activation function, we can more effectively capture the spatial information inherent in graphs. The weights in the non-local gradient and divergence operators are determined based on the graph's adjacency matrix. We apply the proposed method into the architecture of GCN and GraphSAGE, testing them on citation and webpage linking datasets, respectively. Numerical experiments demonstrate its good performance in node classification and generalization capabilities. These results indicate that the graph similarity regularized softmax is effective on both assortative and disassortative graphs.