Training method and device of graph neural network

Abstract

The embodiment of the invention provides a training method of a graph neural network. The method comprises the following steps: firstly, obtaining a relational network diagram, wherein the relational network diagram comprises a plurality of object nodes corresponding to a plurality of business objects; next, for each object node, fusing the node feature of the object node with the node feature of the neighbor node of the object node to obtain a fusion feature of the object node, and forming a fusion feature matrix by a plurality of fusion features corresponding to the plurality of object nodes; utilizing the graph neural network to perform graph embedding processing on the relation network graph to obtain a plurality of embedded vectors corresponding to the plurality of object nodes, the graph neural network comprising an activation function, and determining a plurality of prediction results based on the plurality of embedded vectors; determining a product matrix before and after the fusion feature matrix is processed by the activation function; and determining a training gradient of parameters in the graph neural network based on the product matrix, the plurality of prediction results and the service labels, and further updating the parameters in the graph neural network based on the training gradient.

Description

technical field [0001] The embodiments of this specification relate to the field of computer technology, and in particular to a training method and device for a graph neural network. Background technique [0002] The relationship network diagram is a description of the relationship between entities in the real world, and is currently widely used in various computer information processing. Generally, a relational network graph includes a set of nodes and a set of edges. Nodes represent entities in the real world, and edges represent connections between entities in the real world. For example, in a social network, people are entities, and relationships or links between people are edges. [0003] In many cases, it is hoped to analyze the topological characteristics of nodes, edges, etc. in the relational network graph, and extract effective information from them. The computing method to realize this kind of process is called graph computing. Typically, it is desired to repres...

AI Technical Summary

Problems solved by technology

However, in the training phase of the graph neural network, due to the need to train millions of parameters and the highly non-convex nature of the objective function, conventional training consumes a large amount of computing resources, and it is difficult to guarantee the convergence of the training and the training output. Embedding Effects of Graph Neural Networks

Images