Cargando…
Persona2vec: a flexible multi-role representations learning framework for graphs
Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each node, implicitly assuming that a single representation is enough to capture all...
Autores principales: | Yoon, Jisung, Yang, Kai-Cheng, Jung, Woo-Sung, Ahn, Yong-Yeol |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8022511/ https://www.ncbi.nlm.nih.gov/pubmed/33834106 http://dx.doi.org/10.7717/peerj-cs.439 |
Ejemplares similares
-
Confusion2Vec: towards enriching vector space word representations with representational ambiguities
por: Gurunath Shivakumar, Prashanth, et al.
Publicado: (2019) -
Text-Graph Enhanced Knowledge Graph Representation Learning
por: Hu, Linmei, et al.
Publicado: (2021) -
Malware detection framework based on graph variational autoencoder extracted embeddings from API-call graphs
por: Gunduz, Hakan
Publicado: (2022) -
Experiments with LDA and Top2Vec for embedded topic discovery on social media data—A case study of cystic fibrosis
por: Karas, Bradley, et al.
Publicado: (2022) -
Temporal network embedding framework with causal anonymous walks representations
por: Makarov, Ilya, et al.
Publicado: (2022)