Method and device for training graphic neural network model

Abstract

The embodiment of the invention provides a method and a device for training a graphic neural network model. The method comprises the following steps: acquiring a target training sample and a corresponding target sample label from a sample set; wherein the target training sample corresponds to a target node in a target relationship network graph, the target node has a target node number, the targetrelationship network graph comprises a plurality of nodes and connecting edges between the nodes, each node has a respective corresponding node number, and each connecting edge has a respective corresponding edge number; querying graph information of a target sub-graph of the target relational network graph from pre-stored graph information of the target relational network graph according to thetarget node number and preset parameters; wherein the target sub-graph takes the target node as a central node, and the hop count between each node in the target sub-graph and the target node is lessthan or equal to a preset parameter; and training the graph neural network model by using the graph information of the target sub-graph and the target sample label. Requirements on a machine can be reduced, and training efficiency can be improved.

Description

technical field [0001] One or more embodiments of this specification relate to the computer field, and in particular to a method and device for training a graph neural network model. Background technique [0002] Graph data is a data structure representing connection relationships between people or things. In production and life, it is often necessary to mine information in graph data in order to improve production efficiency or improve human experience. The graph neural network (GNN) algorithm is an industry-leading algorithm for mining information in graph data. [0003] Due to the large scale of graph data, for example, it can reach a scale of one billion nodes and one hundred billion edges. Common machines cannot accommodate such large-scale data. Although there are machines that can accommodate such large-scale data, the training efficiency of the GNN model Also very low. [0004] Therefore, it is hoped that there will be an improved solution that can reduce the requ...

AI Technical Summary

Problems solved by technology

[0003] Due to the large scale of graph data, for example, it can reach a scale of one billion nodes and one hundred billion edges. Common machines cannot accommodate such large-scale data. Although there are machines that can accommodate such large-scale data, the training efficiency of the GNN model also very low

Images