Data classification method and device based on unified optimization target framework graph neural network

Abstract

The embodiment of the invention provides a data classification method and device based on a unified optimization target framework graph neural network. The method comprises the steps of obtaining description information of to-be-classified objects and relationship information between the to-be-classified objects; generating a feature matrix based on the description information, and generating an adjacent matrix based on the relationship information; inputting the feature matrix and the adjacent matrix into a pre-constructed and trained graph neural network to obtain a classification result of each to-be-classified object; wherein the graph neural network is constructed according to a predetermined feature propagation equation, the feature propagation equation is obtained by performing graph filter assignment on the basis of a preset optimization target equation, and the optimization target equation comprises a feature fitting constraint term and a graph Laplace regularization constraint term. A unified optimization target equation of the graph neural network is proposed, assignment is performed on the graph filter to obtain the feature propagation equation, the graph neural network is constructed according to the feature propagation equation, the to-be-classified objects are classified according to the constructed graph neural network, and the classification accuracy can be improved.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a data classification method and device based on a unified optimization target frame graph neural network. Background technique [0002] Graph neural networks (GNNs) are a connection model that captures graph dependencies through message passing between nodes of the graph. Graph neural networks can represent information with arbitrary depth from their neighborhoods. In recent years, graph neural networks have been widely used in various fields such as social networks, knowledge graphs, recommendation systems, question answering systems, life sciences, etc., and can usually be used for object classification. [0003] A well-designed feature propagation equation is a key part of the graph neural network. However, the existing graph neural network does not design corresponding feature propagation equations for different types of feature data. Therefore, the existing g...

AI Technical Summary

Problems solved by technology

[0003] A well-designed feature propagation equation is a key part of the graph neural network. However, the existing graph neural network does not design corresponding feature propagation equations for different types of feature data. Therefore, the existing graph neural network is used to accurately classify data. not high enough

Images