A semi-supervised network representation learning algorithm based on deep compression self-encoder

Abstract

The invention discloses a semi-supervised network representation learning algorithm LSDNE (Labeled Structural Deep Network Embedding) based on a deep compression self-encoder. The method comprises thefollowing steps: building a model, pre-training the input data with a deep belief network (DBN) to obtain the initial values of the model parameters, and taking the adjacency matrix and Laplace matrix of the network as inputs; encoding the network by a self-encoder with deep compression, and obtaining the global structure of the node; using Laplacian feature mapping, and obtaining the local structural features of nodes; using an SVM classifier to classify the known label nodes and optimize the whole model; using the Adam optimization model and obtaining a representation of the node. The invention can simultaneously use the structure information of the network and the label information of the node to carry out network representation learning, and the deep learning model is used, so that the performance of the representation of the node on the label classification task is better than the existing algorithm. Deep compression self-encoder can reduce the over-fitting phenomenon and make the model have better generalization performance.

Description

Technical field [0001] The present invention relates to network representation learning, in particular to a semi-supervised network representation learning algorithm LSDNE (Labeled Structural Deep Network Embedding) using label data and based on a deep learning model. Background technique [0002] Network representation learning is to represent a high-dimensional network in a low-dimensional vector space, aiming to obtain and retain the structural information of the network. A network, its structure can be applied to various tasks, such as community discovery, edge prediction, node classification, etc. However, the traditional network analysis technology has its limitations. First, the complexity of traditional methods is too high to be applied to modern large-scale networks; second, in modern large-scale networks, the link relationship between nodes is very complicated and difficult to observe, which leads to traditional analysis methods It is difficult to give a solution to q...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies in the prior art, the present invention provides a semi-supervised network representation learning algorithm based on deep compression autoencoder, which is used to solve the limitations of existing network representation learning algorithms

Images