Dynamic network representation learning method for social network platform

Abstract

The invention discloses a dynamic network representation learning method for a social network platform, and the method comprises the following steps: numbering all appearing nodes according to input original data; constructing a dynamic network according to the numbered node sequence and the original data; obtaining an adjacency matrix, a self-loop adjacency matrix and a corresponding degree matrix of the dynamic network; taking the obtained matrix as input and sending the matrix to a deep neural network model for learning; and training a neural network model, converting the original high-dimensional sparse matrix into a low-dimensional dense vector, and embedding time sequence information carried by the network into a new vector space. According to the method, feature extraction is carried out on the network data by using the graph convolutional neural network, and potential time sequence information in the network is captured in combination with the LSTM, so that feature informationand time sequence information contained in the high-dimensional network can be captured, and the method has good universality and can be applied to all related network analysis tasks.

Description

technical field [0001] The invention belongs to the technical field of representation learning, and in particular relates to a dynamic network representation learning method oriented to a social network platform. Background technique [0002] Network representation learning aims to represent the nodes in the network into a low-dimensional, real-valued, dense vector form, so that the obtained vector form can have the ability of representation and reasoning in the vector space. At present, the static network representation learning algorithm has been developed in the long run. However, most of the networks in the real world are dynamic rather than static, that is, the nodes or edges in the network will increase or decrease over time. . Simply applying the existing static network representation learning algorithm to each snapshot of the dynamic network usually results in unsatisfactory stability, flexibility, and efficiency. How to design the algorithm to make it more suitable...

AI Technical Summary

Problems solved by technology

For the dynamic network representation learning method using traditional deep learning, since the network data belongs to non-Euclidean space, there is also room for improvement in the feature extraction of traditional deep learning methods on non-Euclidean space data

Images