Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Preference learning mechanism-based overlapping community discovery method and system

A technology of overlapping communities and learning mechanisms, applied in transmission systems, digital transmission systems, instruments, etc., can solve problems such as inaccuracy, algorithm instability analysis results, and different results, and achieve efficient convergence, rapid convergence, Applicable effect

Inactive Publication Date: 2018-09-28
CENT SOUTH UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Community networks include non-overlapping communities and overlapping communities. Most of the community network nodes in real life belong to multiple communities. Everyone’s interests in the network are not single, so overlapping communities are common, and analysis and research through overlapping communities can get results that are more in line with actual needs; at present, most of the discovery methods for discovering overlapping communities only focus on the connection itself and ignore The preference information hidden in the connection is hidden, and most of the current algorithms perform the node update sequence randomly during the label propagation process, which easily leads to different results generated by each algorithm execution, which leads to the instability of the algorithm and inaccurate analysis results

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Preference learning mechanism-based overlapping community discovery method and system
  • Preference learning mechanism-based overlapping community discovery method and system
  • Preference learning mechanism-based overlapping community discovery method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] see figure 1 , this embodiment discloses a method for discovering overlapping communities based on a preference learning mechanism, including the following steps:

[0062] S1: Assign a unique label to each node, set the degree of membership of the node to the label, and then define the importance of the node according to the degree of the node and the local clustering coefficient, where the local clustering coefficient of the node is recorded as C( x), the calculation formula is:

[0063]

[0064] In the formula, N(x) represents the degree of node x, and n represents the number of edges that can be formed between nodes in the set formed by node x and its neighbor nodes;

[0065] The importance of the node is recorded as Importance(x), and the calculation formula is:

[0066] Importance(x)=|N(x)| 2 *C(x);

[0067] S2: According to the importance of the nodes, sort the nodes in order from high to low, define the label similarity, jaccard coefficient and connection ...

Embodiment 2

[0105] This embodiment takes the kite network as an example for analysis and description. First of all, it needs to be clear that the kite network is a small analog network commonly used in the field of complex network community division. The network has 7 nodes and 10 edges. The topology of the network Figure such as image 3 As shown, according to the node importance formula proposed by the present invention, the importance of all nodes in the topology diagram is calculated, and the importance of each node in the kite network is obtained as Figure 4 As shown, the order of each node in the kite network is 4, 1, 3, 5, 7, 2, 6 after sorting the importance of the nodes from high to low. In the initialization, the node ID is used as the initial community label, and the topology diagram after initialization is obtained as follows Figure 5 As shown, then, the nodes perform learning and normalization sequentially according to the above sequence to complete an iterative process, w...

Embodiment 3

[0108] In this embodiment, six real data sets commonly used in this field are selected to verify an overlapping community discovery method based on a preference learning mechanism (hereinafter referred to as PLPA) proposed by the present invention. In addition, four classic algorithms are selected for comparison. On the one hand, the widely used extended modularity index EQ is used as the evaluation index of this experiment. Among them, the experimental environment is: Intel i5-4590 3.2GHz CPU, 8G memory, PC with Windows8 operating system.

[0109] Specifically, the PLPA algorithm is verified by using six datasets commonly used in the field of overlapping community discovery. The parameters of the dataset are shown in Table 1 below:

[0110] Table 1 Real network dataset

[0111]

[0112] In addition, four classic algorithms are used for comparative experiments, more specifically, the four classic algorithms include CPM algorithm, Link algorithm, Copra algorithm and SLPA al...

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

No PUM Login to View More

Abstract

The invention relates to the field of overlapping community discovery in complex networks, discloses a preference learning mechanism-based overlapping community discovery method and system, and aims at rapidly, efficiently, correctly and stably detecting overlapping communities in complex networks through considering preference relationships. The method comprises the following steps of: distributing a unique label for each node, setting a membership degree, to the label, of the node, and defining significance of the node; calculating preference degrees between the nodes; selecting a learning object to normalize the nodes according to the preference degrees, so as to obtain each node relational graph after iteration; and continuously carrying iteration on the basis of each node relational graph after the last iteration, doing the rest in the same manner until iteration is carried out for a set sequence to obtain each final node relational graph, dividing the nodes with same labels intoa same community, considering the nodes with at least two labels as overlapping nodes, and considering communities where the overlapping nodes are located as overlapping communities.

Description

technical field [0001] The invention relates to the field of overlapping community discovery in complex networks, in particular to a method and system for discovering overlapping communities based on a preference learning mechanism. Background technique [0002] In recent years, the research on complex networks has been widely concerned by the academic and commercial circles, especially with the rapid development of web2.0 technology and the popularity of mobile terminals, information sharing networks, blog networks, communication systems, mail networks, SMS The rapid development of online community networks such as online chat rooms has attracted people's attention and has become an indispensable social tool in people's lives, helping people maintain their social relationships in the virtual world. Therefore, it becomes more and more important to evaluate complex systems represented by social network systems. Among them, a hot topic in complex network research is community...

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
no application Login to View More
IPC IPC(8): G06F17/30G06Q50/00H04L12/24
CPCG06Q50/01H04L41/14
Inventor 盛津芳王凯王斌李钊
Owner CENT SOUTH UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com