Cross-social network alignment method fusing relative positions of nodes and absolute distribution

Abstract

The invention provides a cross-social network alignment method fusing relative positions of nodes and absolute distribution. The method comprises the following steps: iteratively deleting minimum degree nodes in a source network and a target network, ending iteration, calculating importance degrees of the nodes, and aligning anchor nodes in the source network and the target network according to the importance degrees of the nodes; in the source network and the target network, calculating the position similarity between the node and each anchor node, and obtaining the comprehensive position similarity vector of the node; calculating a neighbor degree distribution degree vector of the node by adopting a diffusion method; and fusing the comprehensive position similarity vectors and the neighbor degree distribution degree vectors of the nodes, and calculating cross-network node pairs by using the fused vectors to obtain an alignment result of the source network and the target network. According to the method, the precision of network alignment is improved by integrating the comprehensive position similarity vector and the neighbor degree distribution degree vector of the nodes, and the problem that degree distribution is similar and the problem that the alignment effect is sensitive to noise due to the fact that the network scale is too large are effectively avoided.

Description

Technical field [0001] Technical Field The present invention relates to a complex network analysis, more particularly to a relative position of nodes and fusion across social networks absolute alignment method of distribution. Background technique [0002] Network is an efficient data structure, in this interconnected world, it can express the rich relationship, such as co-authoring, e-mail communication and social relationships. Therefore, the data mining community proposed various methods for many tasks on a single network, such as anomaly detection, predictive link and user modeling. However, many joint analysis graph mining tasks involved nodes across multiple networks. The nature of the similarity and alignment problems network is a plurality of definitions FIG. [0003] Research Network alignment or matching problems to find the corresponding network nodes in different networks. Network alignment is critical for recognition of similar users in different social networks, and...

AI Technical Summary

Problems solved by technology

[0009] 1. The node structure in a large network is prone to the same phenomenon, which will interfere with the embedding of computing nodes, so the accuracy of this method is not high in the environment of large data sets

[0010] 2. This method lacks the consideration of the overall structural information of the network, so it is sensitive to the local noise of the nodes

Images