Understanding Graph Embedding Methods and Their Applications
The main goal of graph embedding methods is to pack every node's properties into a vector with a smaller dimension, hence, node similarity in the original complex irregular spaces can be easily quantified in the embedded vector spaces using standard metrics.
Abstract
Related DatabasesWeb of Science You must be logged in with an active subscription to view this.Article DataHistorySubmitted: 20 December 2020Accepted: 23 February 2021Published online: 04 November 2021Keywordsdeep neural networks, high-dimensionality, latent space, similarity, uncertainty quantification, intrinsic dimension, graph embedding at scaleAMS Subject Headings68T07, 05C62, 94A15, 68T37, 68R10, 68T30Publication DataISSN (print): 0036-1445ISSN (online): 1095-7200Publisher: Society for Industrial and Applied MathematicsCODEN: siread