Relational network link predicting method based on generalized relation hidden topic model

Abstract

The invention provides a relational network link predicting method based on a generalized relation hidden topic model and relates the field of computer application. The method includes the steps of S1, pretreating text relational network data, and extracting word bag text features and link relations among documents; S2, building a generalized relation hidden topic link predicting model according to the extracted word bag text features and link relations among documents; S3, training the generalized relation hidden topic link predicting model; and S4, using the trained generalized relation hidden topic link predicting model to predict link relations among documents. The defect that symmetrical relation discrimination functions are unreasonable, and data likelihood of relation discrimination functions, unbalance of two parts of loss functions and approximate reasoning mean field assumption cause non-ideal link relation predicting in the prior art are overcome, and practicality in tasks such as link relation predicting, network recommending and text retrieving is improved evidently.

Description

Technical field [0001] The invention relates to the field of computer applications, and in particular to a relational network link prediction method based on a generalized relational hidden topic model. Background technique [0002] The rapid development of information technology provides Internet user groups with massive, heterogeneous, and interconnected complex network relationship data, including academic paper citation relationship networks and social relationship networks. In-depth analysis of these network data, effective use of the relational network data's association structure and natural network attributes, is conducive to learning more accurate prediction models, and improving the performance of many data mining and prediction tasks, such as recommending academic paper citations and recommending social networking more accurately Internet friends, etc. This is also one of the hot issues that have been widely concerned in the field of data mining and machine learning i...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the deficiencies of the prior art, the present invention provides a relational network link prediction method based on the generalized relational latent topic model; The imbalance between the two parts of the data likelihood and the loss function and the mean field assumption of approximate inference cause the defect of unsatisfactory link relationship prediction performance

Images