Cargando…
Principled approach to the selection of the embedding dimension of networks
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...
Autores principales: | Gu, Weiwei, Tandon, Aditya, Ahn, Yong-Yeol, Radicchi, Filippo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8213704/ https://www.ncbi.nlm.nih.gov/pubmed/34145234 http://dx.doi.org/10.1038/s41467-021-23795-5 |
Ejemplares similares
-
Change in the Embedding Dimension as an Indicator of an Approaching Transition
por: Neuman, Yair, et al.
Publicado: (2014) -
Dimensions, Embeddings, and Attractors
por: Robinson, James C
Publicado: (2010) -
Flavor network and the principles of food pairing
por: Ahn, Yong-Yeol, et al.
Publicado: (2011) -
Who Is the Best Player Ever? A Complex Network Analysis of the History of Professional Tennis
por: Radicchi, Filippo
Publicado: (2011) -
Breaking of the site-bond percolation universality in networks
por: Radicchi, Filippo, et al.
Publicado: (2015)