Cargando…
DDNE: Discriminative Distance Metric Learning for Network Embedding
Network embedding is a method to learn low-dimensional representations of nodes in networks, which aims to capture and preserve network structure. Most of the existing methods learn network embedding based on distributional similarity hypothesis while ignoring adjacency similarity property, which ma...
Autores principales: | Li, Xiaoxue, Li, Yangxi, Shang, Yanmin, Tong, Lingling, Fang, Fang, Yin, Pengfei, Cheng, Jie, Li, Jing |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7302248/ http://dx.doi.org/10.1007/978-3-030-50371-0_42 |
Ejemplares similares
-
A Boosting-Based Deep Distance Metric Learning Method
por: Li, Zilong
Publicado: (2022) -
Distance-Metric Learning for Personalized Survival Analysis
por: Galetzka, Wolfgang, et al.
Publicado: (2023) -
A regression framework for brain network distance metrics
por: Tomlinson, Chal E., et al.
Publicado: (2022) -
Distances in Higher-Order Networks and the Metric Structure of Hypergraphs
por: Vasilyeva, Ekaterina, et al.
Publicado: (2023) -
Obtaining psychological embeddings through joint kernel and metric learning
por: Roads, Brett D., et al.
Publicado: (2019)