Text-enhancing network expression learning method

Abstract

The invention discloses a text-enhancing network expression learning method, and relates to a complex network analysis technology. A new text-information-enhancing network expression learning method is put forward on the basis of non-negative matrix decomposition, and for the network structure, in combination with the first-order and second-order similarity between nodes, network expression is obtained through a decomposition similarity matrix; for the text clustering structure related to the nodes, decomposition is conducted on a text-lexical item matrix to obtain a text clustering affinity matrix, the consistency relationship is established between the network expression and the text clustering structure through the text clustering affinity matrix, and therefore network expression learning is controlled by the network structure and the text clustering structure related to the joints. By means of the method, the network structure is depicted, the text clustering structure related to the joints is also depicted, additional information beside the network structure is added to the network expression learning, the learned nodes are used for expressing more available information, and higher identifiability is achieved.

Description

technical field [0001] The invention relates to the technical field of complex network analysis, in particular to a text-enhanced network representation learning method. Background technique [0002] In the real world, the network is ubiquitous, such as the well-known social network Twitter and the academic paper citation network DBLP, etc. Due to the ubiquity and importance of the network, network analysis has received more and more attention. Various network analysis tasks are widely studied, such as node classification, connection prediction, and community discovery. However, these tasks usually face the sparsity problem brought by the traditional network representation of adjacency matrix. In order to solve this problem, in recent years, network representation learning methods aiming at learning low-dimensional continuous vector representations for each node in the network have aroused the research interest of many scholars. Network representation learning aims to lear...

AI Technical Summary

Problems solved by technology

Although the text information of nodes is closely related to the network structure, there is little related work that takes node text information into consideration in existing network representation learning methods.

Images