2020/04/30 by Weiwei Gu, Aditya Tandon, Yong-Yeol Ahn +1 · 1 citation
Physics and Astronomy · Computer Science · #physics.soc-ph #cs.SI
paper · pdf · doi:10.1038/s41467-021-23795-5
published as Nat. Commun. 12, 3772 (2021) · 13 pages, 5 figures, Supplementary Information available this http://homes.sice.indiana.edu/filiradi/Mypapers/SI_nc.pdf
arxiv created 2021/06/18 · arxiv updated 2021/06/22
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.