A Novel Fuzzy-Based MOPSO Algorithm for Identifying Clusters From Complex Networks.

ICTAI(2022)

引用 0|浏览8
暂无评分
摘要
Many complicated systems can be modeled as complex networks, and a variety of graph clustering algorithms have been proposed to perform accurate clustering analysis for better understanding system behaviors. However, most of them suffer the disadvantage of slow convergence. In this paper, we incorporate multi-objective particle swarm optimization (MOPSO) into a well-established fuzzy clustering algorithm, i.e., FCAN, and propose an improved Fuzzy-based Graph Clustering Algorithm, namely IMFCAN, which retains all the benefits gained with FCAN while achieving significantly fast convergence rate. Specially, IMFCAN enhances the ability of handling the imbalance observed in the distribution of fuzzy membership of nodes by introducing an instance-frequency-weighted regularization (IR) scheme. After that, IMFCAN develops an effective solution to reach a consensus optimization among them by balancing global exploration and local exploitation abilities of particles. Experimental results on four practical datasets demonstrate that IMFCAN performs better than several state-of-the-art clustering algorithm in terms of accuracy and convergence. Hence, IMFCAN is a promising algorithm for addressing the clustering analysis of complex networks.
更多
查看译文
关键词
Complex network,graph clustering,fuzzy membership,multi-objective particle swarm optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要