# **Curvature Graph Network**

- Topic
- Introduction
- Describe CGN
- Working

## Topic
So far we have covered various network which based on graph data but still we have left so much topic. In this tutorial we will talk about curvature graph network which bassically tells us the structural information of our networks. we have seen GCN which tells us to degree information by using neighborhoods and aggregiation principle but not tells about how structurally pair node `conected, which give more information about data. We propose a novel network architecture that incorporates advanced graph structural information, specifically, discrete graph curvature, which measures how the neighborhoods of a pair of nodes are structurally related. The curvature of an edge (x, y) is defined by comparing the distance taken to travel from neighbors of x to neighbors of y, with the length of edge (x, y).. It is a much more descriptive structural measure compared to previously ones that only focus on node specific attributes or limited graph topological information such as degree.`

## Introduction