Efficient Community Detection Based on Label Propagation with Belonging Coefficient and Edge Probability

Label propagation algorithm (LPA) has proven to be an efficient means for finding communities in large complex networks, and many improved methods were proposed, but the performance, stability and time complexity of them still need to be improved. In this paper, we investigate the modularity-specialized label propagation algorithm (LPAm), and find that the time complexity of LPAm greatly increased. We prune the LPAm algorithm by only considering neighbors for updating a node’s label, which degenerates to a Label propagation algorithm with edge probability and retains the same computational efficiency with LPA. Further, we integrate maximum belonging coefficient into LPA and present an advanced label propagation algorithm by combining maximum belonging coefficient and edge probability (LPAbp), which improves the quality of communities and preserves the merit of high speed of LPA. We also discuss the formation of monster community and time complexity of LPA, LPAm, and our algorithm by experiments on real world networks in form of quantitative analysis. Our proposed algorithms were evaluated on fourteen networks of various types and sizes. Experiments show that the LPAbp algorithm sustains the same time complexity with LPA, hinders the formation of monster community, and exhibits significant improvements in the modularity and Normalized mutual information values of community detection.

[1]  Pietro Liò,et al.  Towards real-time community detection in large networks. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  M E J Newman,et al.  Community structure in social and biological networks , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Hristo Djidjev,et al.  A Scalable Multilevel Algorithm for Graph Clustering and Community Structure Detection , 2007, WAW.

[4]  Yiannis Kompatsiaris,et al.  Community detection in Social Media , 2012, Data Mining and Knowledge Discovery.

[5]  Mark E. J. Newman,et al.  Stochastic blockmodels and community structure in networks , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[6]  Réka Albert,et al.  Near linear time algorithm to detect community structures in large-scale networks. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  Lars Backstrom,et al.  Balanced label propagation for partitioning massive graphs , 2013, WSDM.

[8]  Zhen Lin,et al.  CK-LPA: Efficient community detection algorithm based on label propagation with community kernel , 2014 .

[9]  Antoine Girard,et al.  Opinion Dynamics With Decaying Confidence: Application to Community Detection in Graphs , 2009, IEEE Transactions on Automatic Control.

[10]  Jianfeng Feng,et al.  On the Spectral Characterization and Scalable Mining of Network Communities , 2012, IEEE Transactions on Knowledge and Data Engineering.

[11]  Saurabh Goyal,et al.  Like-minded communities: bringing the familiarity and similarity together , 2013, World Wide Web.

[12]  Junhua Tang,et al.  Detecting community structure via synchronous label propagation , 2015, Neurocomputing.

[13]  Athman Bouguettaya,et al.  Trusting the Social Web: issues and challenges , 2013, World Wide Web.

[14]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[15]  ZhengYou Xia,et al.  Community detection based on a semantic network , 2012, Knowl. Based Syst..

[16]  M E J Newman,et al.  Fast algorithm for detecting community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[17]  T. Murata,et al.  Advanced modularity-specialized label propagation algorithm for detecting communities in networks , 2009, 0910.1154.

[18]  Leon Danon,et al.  Comparing community structure identification , 2005, cond-mat/0505245.

[19]  Claudio Castellano,et al.  Community Structure in Graphs , 2007, Encyclopedia of Complexity and Systems Science.

[20]  Philip S. Yu,et al.  Community detection in incomplete information networks , 2012, WWW.

[21]  Boleslaw K. Szymanski,et al.  Towards Linear Time Overlapping Community Detection in Social Networks , 2012, PAKDD.

[22]  Boleslaw K. Szymanski,et al.  Parallel Overlapping Community Detection with SLPA , 2013, 2013 International Conference on Social Computing.

[23]  Peter D. Hoff,et al.  Latent Space Approaches to Social Network Analysis , 2002 .

[24]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[25]  E A Leicht,et al.  Mixture models and exploratory analysis in networks , 2006, Proceedings of the National Academy of Sciences.

[26]  T. Vicsek,et al.  Uncovering the overlapping community structure of complex networks in nature and society , 2005, Nature.

[27]  Marko Bajec,et al.  Robust network community detection using balanced propagation , 2011, ArXiv.

[28]  Srinivasan Parthasarathy,et al.  Efficient community detection in large networks using content and links , 2012, WWW.

[29]  Jie Cao,et al.  Detecting overlapping communities in poly-relational networks , 2015, World Wide Web.

[30]  Xie Lei,et al.  DICH: A framework for discovering implicit communities hidden in tweets , 2015, World Wide Web.

[31]  Maurice Tchuente,et al.  Local Community Identification in Social Networks , 2012, Parallel Process. Lett..

[32]  Steve Gregory,et al.  Finding overlapping communities in networks by label propagation , 2009, ArXiv.

[33]  Huaiyu Wan,et al.  Balanced Multi-Label Propagation for Overlapping Community Detection in Social Networks , 2012, Journal of Computer Science and Technology.

[34]  Tanya Y. Berger-Wolf,et al.  Sampling community structure , 2010, WWW '10.

[35]  Marko Bajec,et al.  Unfolding network communities by combining defensive and offensive label propagation , 2011, ArXiv.

[36]  M. Barber,et al.  Detecting network communities by propagating labels under constraints. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[37]  Jimeng Sun,et al.  MetaFac: community discovery via relational hypergraph factorization , 2009, KDD.

[38]  Chen Wang,et al.  Detecting Overlapping Community Structures in Networks , 2009, World Wide Web.

[39]  Gennaro Cordasco,et al.  Community detection via semi-synchronous label propagation algorithms , 2010 .

[40]  Mark E. J. Newman,et al.  Generalized communities in networks , 2015, Physical review letters.