Training and prediction of hybrid graph neural network model

Abstract

This specification provides a training method of a hybrid graph neural network model. The hybrid graph neural network model includes an encoding function and a decoding function. The method includes the following: using instances corresponding to all targets in training samples and several nearest neighbors of the instances as nodes in a graph, a graph representation vector of each instance is generated by using the encoding function based on graph data of all the instances. t rounds of training are performed on a decoding parameter; and in each round, bs targets are extracted from training samples, a predicted quantity of each target is generated by using the decoding function based on the graph representation vector of the instance corresponding to each target and non-graph data corresponding to each target, and the decoding parameter is optimized based on a loss quantity of the current round that is determined by the predicted quantities and label quantities of the bs targets in the current round. An encoding parameter is optimized based on loss quantities of the t rounds. All the preceding steps are repeated until a predetermined training termination condition is satisfied.