Efficient clustering method based on large-scale network
A clustering method and large-scale technology, applied in the field of network science, can solve the problems such as the interference of effective network relationship mining, difficulty in meeting the requirements of high efficiency and accuracy of large-scale network clustering problems, and low efficiency of network clustering relationship mining. , to achieve high efficiency and accuracy, and improve the efficiency of network clustering
Inactive Publication Date: 2018-12-07
DALIAN UNIV OF TECH
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The increasing network scale makes network clustering relationship mining face the problem of low efficiency, and redundant data interferes with the effective relationship mining of the network.
Clustering algorithms K-means and gSpan are difficult to meet the requirements for efficiency and accuracy in large-scale network clustering problems
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the specific implementation manners of the present invention will be further described in detail below.
[0043] The example of the present invention provides an efficient large-scale network clustering method based on network high-order primitives, the method comprising:
[0044] Step 1: Select a real clusterable data set, and cut the initial input network based on four conditions.
[0045] In the field of academic big data: extract the academic cooperation information of the American Physical Society APS academic data set (2009-2013) and the Microsoft MAG computer discipline (1980-2015) data set respectively, and build a large-scale scholar cooperation network. The APS dataset includes 96,908 papers from 159,724 scholars, and the MAG dataset includes social network domains: select Facebook’s social networks in eight different domains, and the details are shown in Table 1. ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an efficient clustering method based on a large-scale network, adopts a series of network cutting methods to preprocess a large-scale network, and firstly uses triangular primitives as the minimum of network clustering for parallel clustering on the large-scale network according to the core idea of spectral clustering. In a system, the characteristics of inter-cluster nodeconnection in the node cluster define four conditions, the large-scale network is cut, and the modularity is used to optimize the network partition to obtain a sub-atlas with the highest modularity. Finally, the triangular primitives are used as the minimum units of the network for dimensionality reduction parallel clustering to improve the system clustering efficiency. The system is tested underfour partition conditions, and experimental results verify the efficiency and high precision of the clustering system. The invention provides a new and efficient method for large-scale network clustering, and provides a new solution for large-scale network data relation mining.
Description
technical field [0001] The invention relates to an efficient clustering method based on a large-scale network in the field of network science, in particular to an efficient large-scale network clustering method based on network high-order graph elements. Background technique [0002] The complexity of human behavior and social relations has led to an increasing scale of data, and different social individuals, smart devices, and the complex connections among them constitute a complex large-scale network. The increasing network scale makes network clustering relationship mining face the problem of low efficiency, and redundant data interferes with the effective network relationship mining. Clustering algorithms K-means and gSpan are difficult to meet the requirements of high efficiency and accuracy in large-scale network clustering problems. Therefore, high-efficiency and high-precision large-scale network clustering methods need to be further explored by researchers. Conte...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/62
CPCG06F18/23
Inventor 宁兆龙冯玉凡于硕夏锋
Owner DALIAN UNIV OF TECH