An Embedding Method for Heterogeneous Information Networks Based on Edge Sampling

Abstract

The invention discloses a heterogeneous information network embedding method based on edge sampling, which includes the following steps: S1, preprocessing the weight of each edge in an intelligence data set to obtain a walk weight; S2, selecting the first edge from the intelligence element node set i information element nodes are used as the starting point of the walk, and multiple walks of the rated length are performed on the starting point of the walk based on edge sampling to obtain a walk array; S3, repeat step S2 until i is equal to the total number of nodes in the information element node set V| V|, build multiple walk arrays into a walk array set; S4, select a walk array in the walk array set, and construct a training sample based on the walk array, and train a single hidden layer neural network; S5, combine the information The information element nodes in the element node set are input into the trained single-hidden layer neural network to obtain the embedding vector; the invention solves the problem that the existing graph embedding algorithm cannot handle the weighted graph and the walking is limited.

Description

technical field [0001] The invention relates to the technical field of data security, in particular to a heterogeneous information network embedding method based on edge sampling. Background technique [0002] In the prior art, there are few methods for hierarchical classification of intelligence data, and there are only methods for dividing according to user attributes or specific behaviors. This type of method depends on user attributes and behaviors, and the scalability is not strong. In the prior art, there is a method of intelligence analysis. In the push method based on content similarity, keywords and expert scores are used to establish a user interest model, and the recommendation is made after calculating the similarity. The essence is still the content of the basic matrix decomposition, and the disadvantage is that it cannot be solved. The problem of matrix sparsity; the method based on the retrieval system uses different international and domestic online joint ret...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned deficiencies in the prior art, a heterogeneous information network embedding method based on edge sampling provided by the present invention solves the problems that existing graph embedding algorithms cannot handle weighted graphs and limited walks

Images