Embedding Complex Networks

Graph embedding is a transformation of nodes of a graph into a set of vectors. A good embedding should capture the graph topology, node-to-node relationship, and other relevant information about the graph. The main challenge at hand is to ensure that embeddings describe the properties of the graph well. As a result, selecting the best embedding is a challenging task and very often requires domain experts.

In this thesis, we implement a series of extensive experiments with selected graph embedding algorithms, both on real-world and artificial networks. We conclude from these experiments that Node2Vec is the general best choice of algorithm, but that there is no single winner in all tests. Therefore, our main recommendation for practitioners is, if possible, to generate several embeddings for a problem at hand and use a general framework that provides a tool for an unsupervised graph embedding comparison.