Visual analysis method for understanding graph convolutional neural network

Abstract

The invention discloses a visual analysis method for understanding a graph convolutional neural network. The method comprises the following steps of step 1, dividing an input graph structure data setinto a training set, a verification set and a test set; step 2, defining a parameter set, wherein the parameter set comprises a hidden layer number set and a hidden neuron number set; step 3, based onthe defined parameter set, training to obtain a series of graph convolutional neural network models; step 4, designing a hidden layer analysis view, and displaying the influence of hidden layer parameters on the classification accuracy; step 5, designing a loss and accuracy view, and displaying the change of the loss and classification accuracy in the iterative training process of the model; andstep 6, calculating the positions of the nodes in the graph by adopting a GraphTSNE visualization method, designing a graph layout view, and presenting the prediction condition of the nodes under different training step numbers and the difference of the prediction condition of the nodes between the two training step numbers.

Description

technical field [0001] The present invention relates to graph convolutional neural networks, and more particularly to a visual analysis method for understanding graph convolutional neural networks. Background technique [0002] With the development of artificial intelligence, Graph Convolutional Network (GCN) has received extensive attention in recent years. GCNs can be used to process graph data with arbitrary structures, and have been successfully used to handle different tasks, such as making recommendations for recommender systems, predicting traffic conditions, and classifying articles in citation networks, etc. [0003] Although GCN is used to solve various problems, due to its inherent complexity and nonlinear structure, the underlying decision-making process and why the model can achieve good performance is not well understood. Interpreting and understanding deep neural networks is one of the hotspots in artificial intelligence research at this stage. Existing data...

AI Technical Summary

Problems solved by technology

[0006] 2) Various factors will affect the accuracy of GCN model prediction, such as the number of hidden layers, the number of hidden neurons, the number of training steps, etc.

Images