Method and system for predicting heterogeneous network link relationship

Abstract

The invention discloses a method and system for predicting a heterogeneous network linking relation. The method comprises the steps that S1, entities in a heterogeneous network are preprocessed, so that a training set is obtained, wherein the training set comprises observable attributive characteristics of the entities and the observable linking relation of the entities, and the observable attributive characteristics and the observable linking relation are obtained through preprocessing; S2, a heterogeneous network linking relation prediction model is established according to the node types, the number of nodes and a preset node hidden characteristic vector in the heterogeneous network; S3, on the basis of a maximum entropy discriminant criterion, the model is optimized and the optimized linking relation prediction model is obtained; S4, the optimized linking relation prediction model is trained by the training set, so that the trained linking relation prediction model is obtained; S5, the heterogeneous network linking relation is predicted through the trained linking relation prediction model.

Description

technical field [0001] The invention relates to the field of computer applications, in particular to a method and system for predicting heterogeneous network link relationships. Background technique [0002] Link relationship prediction is the primary task of network data statistical analysis. [0003] Existing methods for predicting link relationships in heterogeneous networks include: 1) random walk in display space and its variants; for example, "Supervised Random Walks: Predicting and Recommending Links in Social Networks" proposed by Backstrom L. et al., in WSDM,2011; 2) Low-rank decomposition in implicit space (such as "Link Prediction via Matrix Factorization" proposed by Menon et al., in ECML2011), non-parametric latent feature model (such as "Nonparametric Latent Feature Models for Link Prediction”, in NIPS2009), etc. However, these methods do not utilize the attribute information of the entity or use the attribute of the entity as additional information entered m...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that the existing heterogeneous network link relationship prediction method does not consider the interaction between entities and attributes, and cannot realize the problem of link relationship prediction between various nodes

Images