Zoo Guide to Network Embedding
This is a review paper that synthesizes existing methods for researchers and practitioners in network science, offering no new contributions but organizing incremental knowledge.
The paper provides a user-friendly guide to network embedding literature and current trends, addressing the challenge of assigning embedding spaces to networks for applications like link prediction and node classification.
Networks have provided extremely successful models of data and complex systems. Yet, as combinatorial objects, networks do not have in general intrinsic coordinates and do not typically lie in an ambient space. The process of assigning an embedding space to a network has attracted lots of interest in the past few decades, and has been efficiently applied to fundamental problems in network inference, such as link prediction, node classification, and community detection. In this review, we provide a user-friendly guide to the network embedding literature and current trends in this field which will allow the reader to navigate through the complex landscape of methods and approaches emerging from the vibrant research activity on these subjects.