Network representation learning method under completely unbalanced tags based on approximate intra-class and inter-class constraints

Abstract

The invention discloses a network representation learning method under completely unbalanced tags based on approximate intra-class and inter-class constraints. The method comprises the steps that social network data is obtained, and labeled nodes and nodes belonging to unknown classes already exist in networks; modeling is conducted on network structure information; the modeling is conducted on network intra-class similarities; the modeling is conducted on network inter-class differences; an objective function of network representation learning is constructed; a solution to the objective function is obtained based on an optimization problem solving algorithm, and learned feature results are obtained. According to the method, the intra-class similarities are broadened by allowing nodes of the same tags to be on the same manifold in feature space, the inter-class differences are broadened by removing existing neighbor relationships between nodes of different tags, the method ensures tworequirements within a reasonable range, meanwhile biased results are avoided, and the method is suitable for semi-supervised network representation learning with completely unbalanced labeled data andbalanced labeled data, and is suitable for scenarios where quality of labeled information cannot be guaranteed.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a network representation learning method under completely unbalanced labels based on approximate intra-class and inter-class constraints. Background technique [0002] Among the problems of social network analysis, network representation learning is a very important problem. Its goal is to learn a dense, continuous and low-dimensional vector for each node in the network as its feature representation. Existing works have demonstrated that the learned features are helpful for various important social network data mining tasks, such as information dissemination, node classification, link prediction, and network visualization. [0003] One of the most basic requirements for network representation learning is to reflect the original network structure in the learned feature space. Some early research work mainly maintained the similarity of the nodes with the original link relation...

AI Technical Summary

Problems solved by technology

For completely unbalanced scenarios, that is, some categories do not have any labeled nodes at all, existing semi-supervised learning methods usually do not perform well

And this scene often occurs in practical applications. For example, the famous text network site Wikipedia contains many types of entry pages, such as movies, literature, history, etc., and it is difficult for us to provide some information on all topics on the site. Annotated samples

Images