Node Centralities and Classification Performance for Characterizing Node Embedding Algorithms
This work addresses the immature study of node embedding algorithms for researchers in graph machine learning, but it is incremental as it builds on existing methods without introducing new techniques.
The study tackled the problem of understanding node embedding algorithms by examining their classification performance in relation to graph centrality measures, finding insights into algorithm properties through systematic experiments on six datasets.
Embedding graph nodes into a vector space can allow the use of machine learning to e.g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs. We examine the performance of node embedding algorithms with respect to graph centrality measures that characterize diverse graphs, through systematic experiments with four node embedding algorithms, four or five graph centralities, and six datasets. Experimental results give insights into the properties of node embedding algorithms, which can be a basis for further research on this topic.