A graph-structured data generation method based on deep convolutional generative adversarial networks

Abstract

The invention discloses a graph-structured-data generation method based on deep convolutional generative adversarial networks (DCGAN), and belongs to the field of big-data technology. The method of the invention applies the deep convolutional generative adversarial networks to the generation field of graph-structured data. According to the method of the invention, firstly, actual graph-structureddata are converted into grid structure pictures with uniqueness; then learning of a generation model is carried out through the deep convolutional generative adversarial networks; and finally, specific-scale simulated graph-structured data are generated through the generation model, which is obtained by learning, according to input parameters and requirements. According to the graph-structured-data generation method based on the deep convolutional generative adversarial networks of the invention, features are extracted mainly from the actual graph-structured data to construct the model, and thus attributes which the generated simulated graph-structured data have are enabled to more accord with the actual graph-structured data.

Description

technical field [0001] The invention belongs to the technical field of big data, and more specifically relates to a graph structure data generation method based on a deep convolution generation confrontation network. Background technique [0002] Graph-Structured Model can be seen everywhere in real life, such as social network, transportation network, information network, etc. In the era of big data, data is an asset, and most data resources are in the hands of very few enterprises. This has resulted in the lack of data resources for most researchers. At the same time, the development of a very large-scale graph-structured data processing system also requires very large-scale graph-structured data for testing. In order to meet the above requirements, various types of graph-structured data generation models have been proposed. The purpose of the graph structure data generation model is to generate simulated graph structure data with realistic graph structure data attribut...

AI Technical Summary

Problems solved by technology

[0005] To sum up the above five types of generative models, whether it is a model that manually sets parameters or a model that learns parameters from real graph structure data, there is a deviation between the generated simulation graph structure data attributes and the real graph structure data attributes, and the generated The structural data of the simulation graph cannot also have multiple attributes at the same time

Images