1.运用场景
which is suitable for arbitrary types of information networks:undirected,directed,and/or weighted。
2.创新点
which suits arbitrary types of information networks and easily scales to millions of nodes.It has a carefully designed objective function that preserves both the first-order and second-order proximities;
propose an edge-sampling algorithm for optimizing the objective.The algorithm tackles the limitation of the classical stochastic gradient decent and improves the effectiveness and efficiency of the inference。
3.算法原理
3.1 网络框架
![](https://img2020.cnblogs.com/blog/1722723/202005/1722723-20200531150146009-1584193795.png)
3.2 LINE
4.算法理解
同时考虑first-order proximity and second-order proximity。