论文链接:http://www.cse.cuhk.edu.hk/~jcheng/papers/pge_kdd19.pdf

github链接:https://github.com/yifan-h/PGE

背景

1.图的应用非常广泛  Graphs are ubiquitous today due to the flexibility of using graphs to model data in a wide spectrum of applications.

2.图表示学习可以使图的结构信息(structural information)和节点信息(degrees,kernel functions,local neighborhood structures)得到直接的使用

3.当前主流的图表示模型(plain graphs),only the pure topology, without node/edge labels and properties

定义

【KDD 2019】A Representation Learning Framework for Property Graphs

【KDD 2019】A Representation Learning Framework for Property Graphs

与GraphSAGE和GCN相比,PGE通过引入偏差bias对邻居进行区分以进行邻居聚合,从而进一步提高了分类的准确性,这验证了前面对bias策略重要性的分析。

算法

【KDD 2019】A Representation Learning Framework for Property Graphs

【KDD 2019】A Representation Learning Framework for Property Graphs

相关文章:

  • 2021-08-21
  • 2021-07-16
  • 2021-12-24
  • 2021-06-19
  • 2021-10-30
  • 2021-09-17
  • 2022-12-23
  • 2022-12-23
猜你喜欢
  • 2021-04-16
  • 2021-08-03
  • 2021-10-02
  • 2021-12-04
  • 2021-07-16
  • 2021-05-09
  • 2022-12-23
相关资源
相似解决方案