A Multi-purposed Unsupervised Framework for Comparing Embeddings of Undirected and Directed Graphs

TL;DR

This paper introduces a flexible, scalable unsupervised framework for evaluating and comparing graph embeddings, effectively capturing local and global network properties for both directed and undirected graphs.

Contribution

The authors extend their previous graph embedding evaluation framework to assign local and global scores, enabling unsupervised selection of the best embeddings for various graph types.

Findings

Framework assigns local and global scores to embeddings

Supports undirected, directed, weighted, and unweighted graphs

Facilitates unsupervised selection of optimal embeddings

Abstract

Graph embedding is a transformation of nodes of a network into a set of vectors. A good embedding should capture the underlying graph topology and structure, node-to-node relationship, and other relevant information about the graph, its subgraphs, and nodes themselves. If these objectives are achieved, an embedding is a meaningful, understandable, and often compressed representation of a network. Unfortunately, selecting the best embedding is a challenging task and very often requires domain experts. In this paper, we extend the framework for evaluating graph embeddings that was recently introduced by the authors. Now, the framework assigns two scores, local and global, to each embedding that measure the quality of an evaluated embedding for tasks that require good representation of local and, respectively, global properties of the network. The best embedding, if needed, can be selected in an unsupervised way, or the framework can identify a few embeddings that are worth further investigation. The framework is flexible, scalable, and can deal with undirected/directed, weighted/unweighted graphs.