Graph visualization method based on graph convolution network

Abstract

The invention discloses a graph visualization method based on a graph convolution network. The method comprises the following steps of: 1) for a network G = (V, E) in a target field, embedding nodes in the network G into a low-dimensional Euclidean space to obtain a low-dimensional embedding vector of the network G; wherein the low-dimensional embedded vector comprises feature information of nodesin a network G and topological structure information of the network G; wherein V is a node set, and E is an edge set; 2) constructing the low-dimensional embedded vector into a K neighbor graph, namely a KNN graph, and 3) drawing the KNN graph in a two-dimensional space based on a probability model. According to the method, the learned embedded vector retains the structure information and the feature information of the node at the same time, and the visualization result can be subjected to granularity adjustment.

Description

technical field [0001] The invention belongs to the technical field of network embedding-network visualization, and relates to a graph visualization method based on a graph convolutional network. Background technique [0002] With the advent of the era of big data, the amount of global information data is exploding. Networks have become an important form of expressing complex relationships between data and are ubiquitous in the information world. Social media such as Facebook and WeChat constitute a social network; proteins in organisms constitute a polymer network; various communication media constitute a communication network; smart hardware constitutes the Internet of Things and so on. In addition to being connected to each other, many network nodes also have rich multimedia information such as text, images, audio and video, forming a typical complex information network. By representing and visually drawing complex networks, it is possible to macroscopically analyze the...

AI Technical Summary

Problems solved by technology

[0012] 2. Most of the existing network representation methods are for static networks. If new nodes are added to the network, retraining is required, and the scalability is poor.

[0013] 3. The existing visualization methods are not clear enough to distinguish between classes, and all nodes are drawn on one graph, which cannot reflect the importance of nodes

Images