Semi-supervised network representation learning model based on hierarchical attention mechanism

Abstract

The invention relates to a semi-supervised network representation learning model based on a hierarchical attention mechanism. The semi-supervised network representation learning model is characterizedby comprising the following steps: 1), word-level semantic coding; 2), sentence-level semantic encoding; 3) node text representation; 4) obtaining of a node structure representation vector and a noderepresentation vector; and 5) introduction of a node label under the semi-supervised framework. Based on a hierarchical attention mechanism, the semi-supervised network representation learning modellearns text representation of network nodes, introduces the node label information under the semi-supervised framework, finally, obtains high-quality representation vectors of the nodes, and improvesthe performance of downstream tasks (node classification and link prediction).

Description

technical field [0001] The invention belongs to the technical field of computer applications, and relates to a semi-supervised network representation learning model, in particular to a semi-supervised network representation learning model based on a hierarchical attention mechanism. Background technique [0002] The web is an efficient way to organize different kinds of information in the real world. With the development of information technology, a large amount of data with network structure has accumulated in the Internet. The analysis of these network structure data is of great significance to the development of various industries. The primary task of analyzing network structure data is to comprehensively utilize the feature information in the network to represent network nodes as a low-dimensional, dense vector, also known as network representation learning. After obtaining the representation vector of network nodes, it can be input into existing algorithms to complete...

AI Technical Summary

Problems solved by technology

[0009] Through the search of published patent documents, no published patent documents identical to this patent application have been found

Images