BriefGPT.xyz
Sep, 2019
多尺度属性节点嵌入
Multi-scale Attributed Node Embedding
HTML
PDF
Benedek Rozemberczki, Carl Allen, Rik Sarkar
TL;DR
本文介绍了一种基于 Skip-gram 相似方法的网络嵌入算法,该算法能够从节点周围的本地分布中捕捉节点的信息。我们证明了其嵌入矩阵隐式地对节点-特征的点间互信息进行了因子分解。实验结果表明,我们的算法在社交网络和Web图上具有鲁棒性,计算效率高,且性能优于可比较的模型。
Abstract
We present
network embedding algorithms
that capture information about a node from the local distribution over
node attributes
around it, as observed over random walks following an approach similar to Skip-gram.
→