Node feature extraction method and device of graph structure and storage medium

Abstract

The embodiment of the invention provides a node feature extraction method and device of a graph structure and a storage medium. The node feature extraction method of the graph structure comprises the steps that a to-be-processed graph structure is acquired, the to-be-processed graph structure comprises a plurality of nodes, and part of the nodes correspond to label information; the to-be-processed graph structure is processed, unsupervised node features and supervised node features corresponding to the nodes are determined, and the supervised node features are related to the label information; and based on the unsupervised node features and the supervised node features, determining semi-supervised node features corresponding to the nodes in the to-be-processed graph structure. According to the technical scheme provided by the embodiment of the invention, the semi-supervised node features corresponding to the graph structure can be effectively and accurately obtained based on the unsupervised node features and the supervised node features, and the obtained semi-supervised node features can be used for carrying out classification prediction on nodes without corresponding label information in the to-be-processed graph structure. Therefore, the practicability of the method is improved.

Description

technical field [0001] The present invention relates to the technical field of graph structures, in particular to a graph structure node feature extraction method, device and storage medium. Background technique [0002] Graph structure data refers to describing various complex data objects through the characteristics of nodes and the relationship between nodes. For example, for the citation relationship between articles, each article can be used as a node to generate graph structure data. Based on the graph structure The data is processed to realize the information integration of the articles. [0003] For graph-structured data, the graph-structured data may include multiple nodes, wherein the multiple nodes may include nodes carrying label information and nodes not carrying label information. When analyzing and processing graph-structured data, Data processing operations are often performed directly based on the feature information of nodes carrying label information. Ho...

AI Technical Summary

Problems solved by technology

However, since the graph structure data includes nodes that do not carry label information, and the number of nodes that do not carry label information is generally large, the above does not consider the feature information corresponding to nodes that do not carry label information. The accuracy of data processing on graph structure data is low

Images