BriefGPT.xyz
Jan, 2020
基于扩散图的快速序列嵌入
Fast Sequence-Based Embedding with Diffusion Graphs
HTML
PDF
Benedek Rozemberczki, Rik Sarkar
TL;DR
本文提出了一种名为`Diffusion Graphs`的图嵌入方法，其通过简单的顶点序列生成可以获得更高的计算效率和更加准确的嵌入结果。实验证明，该方法在图中边密度越大时性能越好，同时在社区检测任务中，利用嵌入空间中的聚类节点可以获得比其他序列嵌入方法更好的结果。
Abstract
A
graph embedding
is a representation of graph vertices in a low-dimensional space, which approximately preserves properties such as distances between nodes.
vertex sequence-based embedding
procedures use feature
→