BriefGPT.xyz
Feb, 2018
节点中心性及分类性能与节点嵌入算法的特征化
Node Centralities and Classification Performance for Characterizing Node Embedding Algorithms
HTML
PDF
Kento Nozawa, Masanari Kimura, Atsunori Kanemura
TL;DR
本文研究基于节点嵌入的机器学习方法，重点探讨了节点嵌入算法在不同类型图上应用的表现，通过4种节点嵌入算法、4-5种图核心度量以及6个数据集的系统实验得到了有关节点嵌入算法性质的洞见，为该领域的进一步研究奠定了基础。
Abstract
Embedding graph nodes into a vector space can allow the use of
machine learning
to e.g. predict node classes, but the study of
node embedding algorithms
is immature compared to the natural language processing fie
→