A Multi-purposed Unsupervised Framework for Comparing Embeddings of Undirected and Directed Graphs
This work addresses the challenge of embedding selection for graph analysis, which often requires domain expertise, by providing a flexible and scalable tool for undirected/directed and weighted/unweighted graphs, but it is incremental as it builds on a prior framework.
The authors tackled the problem of selecting the best graph embedding by extending an existing framework to assign local and global scores for evaluating embeddings based on network properties, enabling unsupervised selection or identification of promising embeddings for further analysis.
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.