AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
Different from those node-based overlapping community detection algorithms, Genetic algorithm for overlapping Community Detection utilizes the property of the unique role of links and applies a novel genetic algorithm to cluster on edges

A link clustering based overlapping community detection algorithm

Data Knowl. Eng., no. 1 (2013): 394-404

引用140|浏览63
EI WOS SCOPUS

摘要

There is a surge of community detection study on complex network analysis in recent years, since communities often play important roles in network systems. However, many real networks have more complex overlapping community structures. This paper proposes a novel algorithm to discover overlapping communities. Different from conventional a...更多

代码

数据

0
简介
  • Community detection, as an effective way to reveal the relationship between structure and function of networks, has drawn lots of attention and been well developed.
  • A professor collaborates with researchers in different fields and a person has his family group as well as friend group at the same time
  • All of these objects represent the interaction between communities and play an important role in the stability of the network.
  • In community detection, these objects should be divided into multiple groups, which are known as overlapping nodes [1].
  • The aim of overlapping community detection is to discover such overlapping nodes and communities
重点内容
  • Nowadays, community detection, as an effective way to reveal the relationship between structure and function of networks, has drawn lots of attention and been well developed
  • We propose a genetic algorithm to detect overlapping communities with link clustering, which is named Genetic algorithm for overlapping Community Detection (GaoCD)
  • (2) We investigate structural characteristics of communities discovered by Genetic algorithm for overlapping Community Detection. (3) We further give the intuitive view of communities discovered by Genetic algorithm for overlapping Community Detection on two real networks
  • We propose a genetic algorithm for overlapping community detection based on the link clustering framework
  • Different from those node-based overlapping community detection algorithms, Genetic algorithm for overlapping Community Detection utilizes the property of the unique role of links and applies a novel genetic algorithm to cluster on edges
  • Experiments on artificial and real networks show that Genetic algorithm for overlapping Community Detection can effectively reveal overlapping structure
方法
  • This section validates the effectiveness of GaoCD with extensive experiments. The authors first assess the ability of GaoCD to discover the overlapping nodes on typical networks, and evaluate effectiveness of GaoCD on the artificial and real networks compared with well-established algorithms.
  • GaoCD accurately reveals overlapping communities for all these networks and ensures that all nodes of the network are covered in the partition
  • These networks are toy examples, real networks compose of these basic structures.
  • It is obvious that GaoCD achieves the highest partition density D for most real networks
  • It indicates that the communities found by GaoCD is denser than that of ABL and GA-Net+
结论
  • Through experiments on both artificial and real networks, the authors can find that GaoCD always has the best performance on most networks.
  • The operation improves the link density of communities, and enhances the fitness of individuals (i.e., D)
  • As a result, those individuals without the fine tuning operation will be eliminated during the population evolution due to the low fitness.
  • Those individuals without the fine tuning operation will be eliminated during the population evolution due to the low fitness
  • These eliminated individuals have the common characteristics: discovering tiny communities.
  • Experiments on artificial and real networks show that GaoCD can effectively reveal overlapping structure
表格
  • Table1: Real networks used in experiments
  • Table2: The partition density D on real networks
Download tables as Excel
相关工作
  • Community detection has been well studied in the last ten years, and a number of algorithms have been developed. These community detection algorithms can be roughly divided into two categories, optimization based methods (e.g. GN fast [19]) and heuristic methods (e.g. GN [29]). Both of the algorithms need a criterion to evaluate the community partition. A widely accepted criterion is the modularity Q proposed by Girvan–Newman [29], which quantitatively defines community structure as a node group that is densely intra-connected and sparsely inter-connected. The modularity Q has been widely used as the optimization objection in many algorithms, such as the algorithm using extremal optimization [10] and GN fast [19].

    However, there are many overlapping networks in real world. For example, a person belongs to more than one social group at the same time. With the increase of the number of communities that overlapping nodes belong to, the internal connection among these communities becomes denser. As a result, the modularity Q does not fit for overlapping communities any more [8]. To discover the overlapping structure of networks, many algorithms have been proposed, which can be roughly divided into two categories: node-based algorithms and link-based algorithms.
基金
  • It is supported by the National Natural Science Foundation of China (nos. 60905025, 61074128, 61035003, 71231002)
  • This work is also supported by the National Key Basic Research Program (973 Program) of China (2013CB329603) and the Fundamental Research Funds for the Central Universities
引用论文
  • G. Palla, I. Derenyi, I. Farkas, T. Vicsek, Uncovering the overlapping community structure of complex networks in nature and society, Nature 435 (2005) 814–818.
    Google ScholarLocate open access versionFindings
  • J.B. Pereira, A.J. Enright, C.A. Ouzounis, Detection of functional modules from protein interaction networks, Proteins: Structure, Functions, and Bioinformatics 54 (2004) 49–57.
    Google ScholarFindings
  • J. Baumes, M.K. Goldberg, M.S. Krishnamoorthy, M.M. Ismail, N. Preston, Efficient Identification of Overlapping Communities, ISI, 2005, 27–36.
    Google ScholarFindings
  • S.H. Zhang, R.S. Wang, X.S. Zhang, Identification of overlapping community structure in complex networks using fuzzy c-means clustering, Physica A 374 (2007) 483–490.
    Google ScholarFindings
  • S. Gregory, An Algorithm to Find Overlapping Communities Structure in Networks, PKDD, 2007, 91–102.
    Google ScholarLocate open access versionFindings
  • S. Gregory, A Fast Algorithm to Find Overlapping Communities in Networks, PKDD, 2008, 408–423.
    Google ScholarFindings
  • A. Lancichinetti, S. Fortunato, J. Kertesz, Detecting the overlapping and hierarchical community structure in complex networks, New Journal of Physics 11 (2009) 033015.
    Google ScholarLocate open access versionFindings
  • Y.Y. Ahn, J.P. Bagrow, S. Lehmann, Link communities reveal multi-scale complexity in networks, Nature 466 (2010) 761–764.
    Google ScholarLocate open access versionFindings
  • C. Pizzuti, Overlapping Community Detection in Complex Networks, GECCO, 2009, 859–866.
    Google ScholarFindings
  • J. Duch, A. Arenas, Community detection in complex networks using extremal optimization, Physical Review E 72 (2005) 027104.
    Google ScholarLocate open access versionFindings
  • M. Tasgin, H. Bingol, Community Detection in Complex Networks using Genetic Algorithm, 2006, (arXiv:cond-mat/0604419).
    Findings
  • C. Shi, Z.Y. Yan, Y. Wang, Y.N. Cai, B. Wu, A genetic algorithm for detecting communities in large-scale complex networks, Advance in Complex System 13 (1)
    Google ScholarLocate open access versionFindings
  • J. Baumes, M. Goldberg, M. Krishnamoorthy, M. Magdon-Ismail, N. Preston, Finding Communities by Clustering a Graph into Overlapping Subgraphs, IADIS, 2005, 97–104.
    Google ScholarFindings
  • H.W. Shen, X.Q. Cheng, J.F. Guo, Quantifying and identifying the overlapping community structure in networks, Journal of Statistical Mechanics (2009) P07042.
    Google ScholarLocate open access versionFindings
  • F. Havemann, M. Heinz, A. struck, J. Glaser, Identification of overlapping communities and their hierarchy by locally calculating community-changing resolution levels, Journal of Statistical Mechanics: Theory and Experiment 01 (2011) 01023.
    Google ScholarLocate open access versionFindings
  • H.W. Shen, X.Q. Cheng, K. Cai, M.B. Hu, Detect overlapping and hierarchical community structure in networks, Physica A 388 (8) (2009) 1706–1712.
    Google ScholarLocate open access versionFindings
  • S. Gregory, Finding overlapping communities in networks by label propagation, New Journal of Physics 12 (2010) 10301.
    Google ScholarLocate open access versionFindings
  • J. Xie, K. Szymanski, X. Liu, SLPA: Uncovering Overlapping Communities in Social Networks via a Speaker–Listener Interaction Dynamic Process, ICDMW, 2011, 344–349.
    Google ScholarLocate open access versionFindings
  • R. Guimera, L.A.N. Amaral, Functional cartography of complex metabolic networks, Nature 433 (2005) 895–900.
    Google ScholarLocate open access versionFindings
  • S. Kelley, The existence and discovery of overlapping communities in large-scale networks, Ph.D. thesis Rensselaer Polytechnic Institute, Troy, NY, 2009.
    Google ScholarFindings
  • A. Lancichinetti, F. Radicchi, J.J. Ramasco, S. Fortunato, Finding statistically significant communities in networks, PLoS One 6 (4) (2011) 18961.
    Google ScholarLocate open access versionFindings
  • S. Zhang, R.S. Wang, X.S. Zhang, Uncovering fuzzy community structure in complex networks, Physical Review E 76 (2009) 046103.
    Google ScholarLocate open access versionFindings
  • W. Ren, G. Yan, X. Liao, L. Xiao, Simple probabilistic algorithm for detecting community structure, Physical Review E 79 (2009) 036111.
    Google ScholarLocate open access versionFindings
  • M. Magdon-Ismail, J. Purnell, Fast overlapping clustering of networks using sampled spectral distance embedding and GMMs, Tech. rep., Rensselaer Polytechnic Institute, 2011.
    Google ScholarFindings
  • K. Nowicki, T.A.B. Snijders, Estimation and prediction for stochastic blockstructures, Journal of the American Statistical Association 96 (455) (2001) 1077–1087.
    Google ScholarLocate open access versionFindings
  • P. Latouche, E. Birmele, C. Ambroise, Overlapping stochastic block models with application to the French political blogosphere, The Annals of Applied Statistics 5 (2011) 309–336.
    Google ScholarLocate open access versionFindings
  • A. McDaid, N. Hurley, Detecting highly overlapping communities with model-based overlapping seed expansion, Advances in Social Networks Analysis and Mining (2010) 112–119.
    Google ScholarLocate open access versionFindings
  • Q. Lu, G. Korniss, B.K. Szymanski, The naming game in social networks: community formation and consensus engineering, Journal of Economic Interaction and Coordination 4 (2009) 221–235.
    Google ScholarLocate open access versionFindings
  • M. Girvan, M.E.J. Newman, Community structure in social and biological networks, Proceedings of the National Academy of Sciences of the United States of America 99 (2002) 7821–7826.
    Google ScholarLocate open access versionFindings
  • A. Lancichinetti, S. Fortunato, Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities, Physical Review E 80 (2009) 016118.
    Google ScholarLocate open access versionFindings
  • L. Danon, A. Diaz-Guilera, J. Duch, A. Arenas, Comparing community structure identification, Journal of Statistical Mechanics: Theory and Experiment (2005) P09008.
    Google ScholarLocate open access versionFindings
  • S. Fortunato, M. Barthelemy, Resolution limit in community detection, PNAS 104 (1) (2007) 36–41.
    Google ScholarLocate open access versionFindings
  • J.M. Kumpulä, M. Kivel, K. Kaski, J. Saramäki, Sequential algorithm for fast clique percolation, Physical Review E 78 (2008) 026109.
    Google ScholarLocate open access versionFindings
  • Q. Ye, B. Wu, Z.X. Zhao, B. Wang, Detecting Link Communities in Massive Networks, ASONAM, 2011, 71–78.
    Google ScholarFindings
  • J. Xie, S. Kelly, B.K. Szymanski, Overlapping community detection in networks: the state of the art and comparative study, ACM Computing Surveys, 2012.
    Google ScholarLocate open access versionFindings
  • I. Psorakis, S. Roberts, M. Ebden, Overlapping community detection using Bayesian nonnegative matrix factorization, Physical Review E 83 (2011) 066114. Chuan Shi received the B.S. degree from the Jilin University, Changchun, Jilin, 2001, the M.S. degree from the Wuhan University, Hubei, in 2004, and Ph.D. degree from the Institute of Computing Technology, Chinese Academy of Sciences, Beijing, in 2007. He joined the School of Computer of Beijing University of Posts and Telecommunications as a lecturer in 2007, and is an associate professor at present. His research interests are in machine learning, data mining, and evolutionary computation. He has published more than 30 papers in refereed journals and conferences.
    Google ScholarLocate open access versionFindings
  • Yanan Cai received the B.S. degree from the University of Electronic Science and Technology of China, Chengdu, Sichuan, 2009. Then she studied in Beijing University of Posts and Telecommunications as a postgraduate student from 2009, and graduated in 2012. Her research interests are machine learning, data mining, and evolutionary computation.
    Google ScholarLocate open access versionFindings
  • Bin Wu received the Ph.D. degree from the Institute of Computing Technology, Chinese Academy of Sciences, Beijing, in 2002. He is a senior member of CCF. He joined the School of Computer of Beijing University of Posts and Telecommunications as a lecturer in 2002, and is a professor at present. His research interests are in data mining, complex network, and cloud computing. He has published more than 100 papers in refereed journals and conferences.
    Google ScholarLocate open access versionFindings
0
您的评分 :

暂无评分

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn