Generation of graph embedding vectors based on graph isomorphism problem

Graph theory is the main theory for handling data with complex relationships: social networks, protein structures, and web page links. In graph theory, an adjacency matrix represents a finite graph structure as a square matrix. Additionally, a graph embedding vector is a low-dimensional vector that extracts the features of a graph. However, adjacency matrices have a drawback of being sensitive to graph vertex ordering changes. In this study, we propose a neural network model using graph isomorphism problem to generate new graph embedding vectors. Experimental results showed that the embedding vectors are robust to vertex reordering.