Cited by Lee Sonogan
Network embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension – small enough to be efficient and large enough to be effective – is challenging but necessary to generate embeddings applicable to a multitude of tasks. Existing strategies for the selection of the embedding dimension rely on performance maximization in downstream tasks. Here, we propose a principled method such that all structural information of a network is parsimoniously encoded. The method is validated on various embedding algorithms and a large corpus of real-world networks. The embedding dimension selected by our method in real-world networks suggest that efficient encoding in low-dimensional spaces is usually possible.
Publication: Nature Communications (Peer-Reviewed Journal)
Pub Date: 18 June 2021 Doi: https://doi.org/10.1038/s41467-021-23795-5
https://www.nature.com/articles/s41467-021-23795-5#citeas (Plenty of sections, figures and references in this article)