A Comparison of Explicit and Implicit Graph Embedding Methods for Pattern Recognition

In recent years graph embedding has emerged as a promising solution for enabling the expressive, convenient, powerful but computational expensive graph based representations to benefit from mature, less expensive and efficient state of the art machine learning models of statistical pattern recognition. In this paper we present a comparison of two implicit and three explicit state of the art graph embedding methodologies. Our preliminary experimentation on different chemoinformatics datasets illustrates that the two implicit and three explicit graph embedding approaches obtain competitive performance for the problem of graph classification.