A multi-purposed unsupervised framework for comparing embeddings of undirected and directed graphs. (28th September 2022)

• Record Type: Journal Article
• Authors: Kamiński, Bogumił; Kraiński, Łukasz; Prałat, Paweł; Théberge, François
• Is Part Of: Network science. Volume 10:Number 4(2022)
• Page Start: 323
• Page End: 346
• Publication Date: 2022-09-28
• Subjects: graph embeddings -- null models -- evaluation of node embeddings; Social networks -- Research -- Periodicals; System analysis -- Periodicals; System theory -- Periodicals; Computer science -- Periodicals; 003.72
• DOI: 10.1017/nws.2022.27
• Languages: English
• ISSNs: 2050-1242

Abstract

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 in [15]. 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 and scalable and can deal with undirected/directed and weighted/unweighted graphs.