Abstract

The research on complex networks is a hot topic in many fields, among which community detection is a complex and meaningful process, which plays an important role in researching the characteristics of complex networks. Community structure is a common feature in the network. Given a graph, the process of uncovering its community structure is called community detection. Many community detection algorithms from different perspectives have been proposed. Achieving stable and accurate community division is still a non-trivial task due to the difficulty of setting specific parameters, high randomness and lack of ground-truth information. In this paper, we explore a new decision-making method through real-life communication and propose a preferential decision model based on dynamic relationships applied to dynamic systems. We apply this model to the label propagation algorithm and present a Community Detection based on Preferential Decision Model, called CDPD. This model intuitively aims to reveal the topological structure and the hierarchical structure between networks. By analyzing the structural characteristics of complex networks and mining the tightness between nodes, the priority of neighbor nodes is chosen to perform the required preferential decision, and finally the information in the system reaches a stable state. In the experiments, through the comparison of eight comparison algorithms, we verified the performance of CDPD in real-world networks and synthetic networks. The results show that CDPD not only has better performance than most recent algorithms on most datasets, but it is also more suitable for many community networks with ambiguous structure, especially sparse networks.

Highlights

  • IntroductionGreat progress has been made in the research of complex networks. Complex network theory is widely used in social, economic, biological, transportation, and other fields

  • Today, great progress has been made in the research of complex networks

  • Some scholars have confirmed that two different evaluation indicators may have the opposite conclusions on the same experimental results [8]. This experiment selects multiple commonly used evaluation indexes to evaluate the above nine algorithms community detection areas, such as Normalized Mutual Information (N MI) [38], Adjusted Rand Index (ARI) [39] and Cluster Purity [40]

Read more

Summary

Introduction

Great progress has been made in the research of complex networks. Complex network theory is widely used in social, economic, biological, transportation, and other fields. Far, exploring community structure in complex networks has attracted great attention. Community structures that are called groups, clusters, cohesive subgroups or modules in different contexts are an important research direction in complex networks. As an important character of complex networks, the division of community structure can deeply understand the function of each community in the network and the relationship with the whole network function, and explore the relationship between different communities in the network, which is helpful in understanding the network topology [5]. A large number of community detection algorithms based on various theories have emerged in the past years. All algorithms have their own advantages and shortcomings. With the increasing complexity of the network, accurate and efficient partitioning in complex networks is still a hot research direction, which attracts numerous people to confront the challenge

Basic Idea
Contributions
Related Work
Basic Formula Principle and Concepts
Preferential Decision Model Based on Dynamic Iteration
Community Detection Based on the Preferential Decision Algorithm
Experiment
Comparing Algorithms
Synthetic Networks
Real-World Networks
Evaluation Metrics
Performance Evaluation
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call