Keywords:
community detection

Title:
A Modularity Maximization Algorithm for Community Detection in Social Networks with Low Time Complexity

Keywords:
Community Detection, Social Networks

Abstract:
... with dense connections within communities and sparse connections between communities. Community detection has recently attracted considerable attention in the field of data ... the field of data mining and social network analysis. Existing community detection methods require too much space and are very time consuming ...

References:
S. Fortunato, Community detection in graphs, Physics Reports, 486, 75-174 (2010).
P. De Meo, E. Ferrara, G. Fiumara, A. Provetti, Generalized Louvain Method for Community Detection in Large Networks. Proc. of the 11th International Conference On Intelligent Systems Design And Applications, pp. 88-93, 2011.

Full Text:
A Modularity Maximization Algorithm for Community Detection in Social Networks with Low Time ComplexityA Modularity Maximization Algorithm ... Social Networks with Low Time ComplexityA Modularity Maximization Algorithm for Community Detection in SocialNetworks with Low Time ComplexityMohsen ArabDepartment of Computer ScienceIASBSZanjan, ... and space complexity and goodaccuracy as well.I. INTRODUCTIONIn recent years, community detection has been in thecenter of attention due to its wide ... different groups or communities in a network evolve.The issue of community detection closely correspondsto the idea of graph partitioning in computer scienceand ... detectionalgorithms. We follow a bottom up approach in which westart community detection by considering every vertex ortwo vertices as preliminary communities. Then ... due to the opening a newera in the ?eld of community detection. . This method usesa new similarity measure called edge betweenness. ...
... graph structure. The complexity is parameterdependent.III. OUR WORKOur idea for community detection is generally basedon ?nding small communities (i.e. sub-communities) andthen merging ... the modularity maximizationstrategy on these preliminary communities that will resultin community detection with higher modularity value.In this paper, subcommunity means small communityand ...
... Section V we will show thatthis will result in poor community detection. . It is a goodidea to cluster neighbor vertices with ...
... graph. As the weighting algorithm willonly be used in preliminary community detection stageand in real graphs which are sparse, D is very ... more accurate preliminaries and as the result,the output of the community detection algorithm will havebetter modularity value.Next step is reducing space complexity ...
... single member subcommunities. As a result and afterrunning the preliminary community detection algorithm,graph will be divided into small communities which haveonly one ... of the edges of the graph(i.e. m). Requiredspace for preliminary community detection is O(m).Running time of this stage is mainly concerned with ... community ci to community cj .Figure 2. Result of preliminary community detection algorithm onKarate Network.If each pair of these connected communities are ... modularity.Figure 3. Scheme of merging subcommunities on subcommunitiesobtained by preliminary community detection algorithm on the Karategraph. the number above arrows refers to ... weighting algo-rithm with time complexity O(R.m) and space complexityO(m), preliminary community detection with time com-plexity O(m.log(m)) and space complexity O(m) and?nally merging ...
... R = ?log(n)?. So, the time complexity ofthe the proposed community detection algorithm will beO(D.n.log(n)). For real graphs which are sparse (D ...
... complex networksin nature and society, Nature 435, 814 (2005).[8] S.Fortunato, Community detection in graphs, Physics Re-ports, 486, 75-174 (2010).[9] M. E. J. ... E. Ferrara, G. Fiumara, A. Provetti, Gener-alized Louvain Method for Community Detection in LargeNetworks. Proc. of the 11th International Conference OnIntelligent Systems ...

Title:
A user interaction based community detection algorithm for online social networks

Keywords:
community detection

Abstract:
<p>Existing community detection techniques either rely on content analysis or only consider the ... limitations of existing approaches, we propose a novel solution of community detection

References:
H. Dev, M. E. Ali, and T. Hashem. User interaction based community detection in online social networks. In Database Systems for Advanced Applications, volume 8422, pages 296--310. 2014.

Full Text:
A User Interaction Based Community Detection Algorithmfor Online Social NetworksHimel Dev?Department of Computer Science and EngineeringBangladesh ... Science and EngineeringBangladesh University of Engineering and Technology, Dhaka, Bangladeshhimeldev@gmail.comABSTRACTExisting community detection techniques either rely on con-tent analysis or only consider the ... the limitations of existing approaches, we propose anovel solution of community detection in OSNs.Categories and Subject DescriptorsH.2.8 [Database Management]: Database Applications?Data MiningKeywordsCommunity ... DescriptorsH.2.8 [Database Management]: Database Applications?Data MiningKeywordsCommunity Detection, Social Networks1. INTRODUCTIONThe community detection involves grouping of similar usersinto clusters, where users in a ... than the other members in the network. Wepropose a novel community detection technique that con-siders the structure of the social network and ... de-grades in networks with rich contents, e.g., OSNs.3. METHODOLOGYThe proposed community detection algorithm has fourphases. In the first phase, the algorithm quantifies ...
... interaction and to incorporate this special type of in-teraction, our communication detection algorithm providesa threshold value for each established friendship link.Average Number ... incorporate this issue in quantifying the interactionbetween users for our community detection algorithm, wetake relative interaction into account. To quantify the im-pact ...
... H. Dev, M. E. Ali, and T. Hashem. User interactionbased community detection in online social networks.In Database Systems for Advanced Applications, volume8422, ...

Title:
Circle based community detection

Keywords:
community detection

Abstract:
... effecient network analysis. In particular we consider the task of community detection in social networks. Nowadays social networking sites allow users to ... detecting better community structures. We pose this task as a community detection problem where the algorithm does not have the information about ... that results obtained are better than the results obtained by community detection

References:
S. Fortunato. Community detection in graphs. Physics Reports, 486(3--5), 2010.
E. Jaho, M. Karaliopoulos, and I. Stavrakakis. Iscode: a framework for interest similarity-based community detection in social networks. In Workshop on Network Science for Communication Networks (NetSciCom), 2011.

Full Text:
... effecient network analysis. In par-ticular we consider the task of community detection in socialnetworks. Nowadays social networking sites allow users tocategorize their ... detecting better community struc-tures. We pose this task as a community detection problemwhere the algorithm does not have the information aboutthe underlying ... shows that results obtained are better thanthe results obtained by community detection ... over the origi-nal graph.KeywordsSocial Networks, Community Detection1. INTRODUCTIONThe problem of community detection in social networksis not a recent one and has been ... the entire graph. For instance, afamous example and application of community detection isshown by Zachary?s karate club dataset, which is also usedas ... karate club dataset, which is also usedas baseline for evaluating community detection algorithms.The dataset consist of 34 vertices, each representing mem-ber of ... from Permissions@acm.orgICARE 2013 New Delhi, IndiaCopyright 2013 ACM 978-1-4503-2320-8 ...$15.00.of community detection is to maximize the intra-communitysimilarity and minimize the inter-community similarity. ...
... [15] is one of the best popular qual-ity functions for community detection nowadays. Optimiz-ing modularity is proved to be a NP-Complete problem ... is done by Pan et Al. [16], whopresented an agglomerative community detection methodbased on node similarity. The method takes into accountstructural similarity ... edge weights based on their similarity and thendoes a weighted community detection. . Both of these worksrequire edge information of the entire ...
... are considered for community detection.Over this induced graph, we run community detection algo-rithm which aims to maximize modularity. For our exper-iments, we ... posi-tive non-zero weight is taken into the induced graph whenrunning community detection algorithm.Figure 2 displays the probability value distribution. Thedistribution in both ...
... the spread of information cascades. This lies at theintersection of community detection algorithms and informa-tion diffusion. It is very vital as it ... is to study the effectivenessof such an approach over other community detection qualitymetrics like conductance, triangle participation ratio (TPR),Cut Ratio, Flake out ... Arenas. Community identificationusing extremal optimization. Phys. Rev., 72(027104),2005.[8] S. Fortunato. Community detection in graphs. PhysicsReports, 486(3-5), 2010.[9] M. Girvan and M. Newman. ...

Title:
Are Evolutionary Computation-Based Methods Comparable to State-of-the-art non-Evolutionary Methods for Community Detection?

Keywords:
community detection

Abstract:
... which have dense intra-group connections and relatively sparse inter-group connections. Community detection is of great importance in various domains, where real-world complex ... other state-of-the-art methods? While several works compare state-of-the-art methods for community detection (see [8] and [11] for recent surveys), we are unaware ... in various ways, we conclude that evolutionary computation-based method for community detection have indeed developed to hold their own against other methods ...

References:
J. Chen and Y. Saad. Dense subgraph extraction with application to community detection. IEEE Trans. Knowl. Data Eng., 24(7):1216--1230, 2012.
C. Liu, J. Liu, and Z. Jiang. A multiobjective evolutionary algorithm based on similarity for community detection from signed social networks. IEEE Trans. Cybernetics, 44(12):2274--2287, 2014.
J. Liu, W. Zhong, H. A. Abbass, and D. G. Green. Separated and overlapping community detection in complex networks usingmultiobjective evolutionary algorithms. In Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2010, Barcelona, Spain, pages 1--7, 2010.
C. Pizzuti. A multi-objective genetic algorithm for community detection in networks. In ICTAI 2009, 21st IEEE International Conference on Tools with A.I., New Jersey, USA, pages 379--386, 2009.
C. Shi, Y. Cai, D. Fu, Y. Dong, and B. Wu. A link clustering based overlapping community detection algorithm. Data Knowl. Eng., 87:394--404, 2013.
J. Su and T. C. Havens. Fuzzy community detection in social networks using a genetic algortihm. In Fuzzy Systems (FUZZ-IEEE), 2014 IEEE International Conference on, pages 2039--2046, July 2014.
P. Wadhwa and M. Bhatia. Community detection approaches in real world networks: A survey and classification. IJVCSN, 6(1):35{51, 2014.
J. Xie and B. K. Szymanski. Towards linear time overlapping community detection in social networks. In Advances in Knowledge Discovery and Data Mining 2012.

Full Text:
Are Evolutionary Computation-Based MethodsComparable to State-of-the-art non-Evolutionary Methodsfor Community Detection? ?Ami HauptmanComputer Science DepartmentSapir Academic CollegeM. P. Hof Ashkelon, Israelamih@mail.sapir.ac.ilABSTRACTOne ... onother state-of-the-art methods? While several works com-pare state-of-the-art methods for community detection (see[8] and [11] for recent surveys), we are unaware of ... and thushave been studied extensively (see [8] and [11] for recentsurveys).Community detection may reveal important informationabout the studied system. The most distinct ... detecting central and outlier nodes, graph hierarchyand shortest paths.However, as community detection is closely related to theclique problem, it is very hard ...
... Based Methods compared to non-Evolutionary Meth-ods (non-EC) applied to The Community Detection Prob-lem. Note: n = |V |Aspect EC non-ECMaximal Network Nodes ... J. Chen and Y. Saad. Dense subgraph extraction withapplication to community detection. . IEEE Trans. Knowl.Data Eng., 24(7):1216?1230, 2012.[2] P. Gopalan and ... and Z. Jiang. A multiobjective evolutionaryalgorithm based on similarity for community detection fromsigned social networks. IEEE Trans. Cybernetics,44(12):2274?2287, 2014.[5] J. Liu, W. ... Zhong, H. A. Abbass, and D. G. Green.Separated and overlapping community detection in complexnetworks using multiobjective evolutionary algorithms. InProceedings of the IEEE ...
... 2014.[12] J. Xie and B. K. Szymanski. Towards linear timeoverlapping community detection in social networks. InAdvances in Knowledge Discovery and Data Mining ...

Keywords:
community detection

Abstract:
<p>The problem of community detection has recently been studied widely in the context of the ... of the web and social media networks. Most algorithms for community detection assume that the entire network is available for online analysis. ... costs. In this context, we will discuss algorithms for integrating community detection with network discovery. We will tightly integrate with the cost ... with the cost of actually discovering a network with the community detection process, so that the two processes can support each other ...

References:
S. Fortunato, Community detection in graphs, PhysicsReports, 486(3), pp. 75--174, 2010.
. Lin, X. Kong, P. Yu, Q. Wu, Y. Jia, andC. Li, Community detection in incomplete information networks, WWW Conference, pp. 341--350, 2012.
T. Yang, R. Jin, Y. Chi, and S. Zhu, Combining link and content for community detection: a discriminative approach, ACM KDD Conference, pp. 927--936, 2009.
S. Fortunato and M. Barthelemy, Resolution limit in community detection, Proceedings of the National Academy of Sciences , 104(1), pp. 36--41, 2007.

Full Text:
... NY, USAcharu@us.ibm.comJiawei HanUniversity of Illinois atUrbana-ChampaignUrbana, IL, USAhanj@illinois.eduABSTRACTThe problem of community detection has recently been stud-ied widely in the context of the ... of the web and social media net-works. Most algorithms for community detection assumethat the entire network is available for online analysis. Inpractice, ... discoverycosts. In this context, we will discuss algorithms for inte-grating community detection with network discovery. Wewill tightly integrate with the cost of ... integrate with the cost of actually discovering anetwork with the community detection process, so that thetwo processes can support each other and ...
... 5 contains the conclusions and summary.1.1 Related workThe problem of community detection is related to thatof finding dense regions in the underlying ... to thatof finding dense regions in the underlying graph [11, 26].Community detection
... dynamic communities are studied in [1, 7, 8]. Theproblem of community detection has also been studied inthe context of combining node and ... effectiveness [20, 24, 27]. Some work has beendone [17] on community detection with incomplete informa-tion networks with the use of available content. ...
... method.We note that some of the afore-mentioned goals are uniqueto community detection, , and others are unique to networkdiscovery, and yet others ...
... merged into the existing network, it is naturally requiredthat the community detection algorithm can be incremen-tally updated and the new partition must ...
... of some nodes are changed, and the parameters inthe generative community detection model, e.g., qij and ?i,are updated. However, with the expansion ...
... as thenetwork expands, new discovered ?meaningful? nodes canhelp improve the community detection performance.DBLP dataset: It is a collection of bibliographic informa-tion on ... discovery part is our main focus, we maintain1http://www.informatik.uni-trier.de/ ley/db/2http://www.imdb.com/the same community detection algorithm discussed in Sec-tion 3.2 while testing different network discovery ... the network as possible. In some cases,this can help the community detection process, since itprovides a greater amount of information about the ... both random sampling and greedy approachdo not depend on the community detection results, we stillrun the UpdateCommunity function after each run of ...
... does not necessarily help to add furtherstructural information to the community detection process.In terms of the relative behavior of our two algorithms, ...
... process. It is evident that evenin this case, both our community detection schemes weresuperior the baselines. While the curves of our proposedstrategies ... this paper suggest that it can be fruitful tointegrate the community detection and network discovery125Budget50010001500 3000 5000Purity0.730.740.750.760.770.78Synthetic (? = 0.8) =0 =0.05 =0.1 =1.0Budget500 1500 3000 ...
... very large networks, PhysicalReview, E 70(6), 066111, 2004.[10] S. Fortunato, Community detection in graphs, PhysicsReports, 486(3), pp. 75?174, 2010.[11] D. Gibson, R. ... X. Kong, P. Yu, Q. Wu, Y. Jia, and C. Li,Community detection in incomplete informationnetworks, WWW Conference, pp. 341?350, 2012.[18] Y.-R. Lin, ... Jin, Y. Chi, and S. Zhu, Combining linkand content for community detection: : a discriminativeapproach, ACM KDD Conference, pp. 927?936, 2009.[25] S. ...

Title:
CoDEM: An Ingenious Tool of Insight into Community Detection in Social Networks

Keywords:
community detection

Abstract:
... in social network analysis. However, performances of multifarious approaches to community detection are seldom evaluated in a suite of systematic measurements. Furthermore, ... a tool called <b>CoDEM</b> to make both quality evaluations of community detection and an in-depth mining for pivotal nodes inside communities. This ... nodes inside communities. This tool integrates several effective approaches to community detection, , establishes an overall evaluation system and gets the multi-dimensional ...

References:
J. Chen and Y. Saad. Dense subgraph extraction with application to community detection. IEEE TKDE, 24(7):1216--1230, 2012.
R. R. Khorasgani, J. Chen, and O. R. Zaïane. Top leaders community detection approach in information networks. In SNMA, 2010.
J. Xie, S. Kelley, and B. K. Szymanski. Overlapping community detection in networks: The state-of-the-art and comparative study. ACM Computing Surveys (CSUR), 45(4):43, 2013.

Full Text:
... in social network analysis. However, performances of multifar-ious approaches to community detection are seldom evaluated in asuite of systematic measurements. Furthermore, we ... build a tool called CoDEM to makeboth quality evaluations of community detection and an in-depthmining for pivotal nodes inside communities. This tool ... pivotal nodes inside communities. This tool integratesseveral effective approaches to community detection, , establishesan overall evaluation system and gets the multi-dimensional rank-ing ... communities. More specifically, CoDEM has the fol-lowing characteristics:? Many well-performed community detection approaches ofvarious categories are integrated in this tool, including Newman-Clauset ...
... The Core Detector is mainly respon-sible for the implementation of community detection approaches.Apart from that, the detector is extendible and any other ... Fagin algorithm as an example.Core Evaluation Layer. With insight into community detection, ,the Evaluator covers both effectiveness and accuracy. In CoDEM,comparisons are ...
... sound design. Besides the approaches alreadyadopted in this tool, other community detection approaches can beappended easily.5. CONCLUSIONSCoDEM is designed for customizable evaluations ... J. Chen and Y. Saad. Dense subgraph extraction withapplication to community detection. . IEEE TKDE,24(7):1216?1230, 2012.[2] A. Clauset, M. E. Newman, and ...

Keywords:
community detection

Abstract:
<p>We present the results of a community detection analysis of the Wikipedia graph. Distinct communities in Wikipedia contain ...

Full Text:
... System Programming,Russian Academy of Sciencesrekouts@ispras.ruABSTRACTWe present the results of a community detection analysisof the Wikipedia graph. Distinct communities in Wikipe-dia contain semantically ... Representation]: Semantic Networks;H.3.3 [Information Search and Retrieval]: ClusteringGeneral TermsExperimentationKeywordsGraph analysis, community detection, , Wikipedia1. INTRODUCTIONThe category structure in Wikipedia is created by ... to au-tomatic hierarchical organization of Wikipedia articles. Weapply a state-of-the-art community detection algorithm toWikipedia graph to identify individual communities. Thesecontain semantically related ... nodes calledcommunities, which are in turn sparsely connected with eachother. Community detection algorithms analyze node con-nections in a graph and divide it ... intra-connectedcomponents, the largest with 1.1M nodes and 4.6M edges.Running the community detection algorithm on this compo-nent took over four days and produced ...
... future work,however the initial experiments demonstrate the potentialof our method.The community- -detection analysis is fully language-in-dependent. Thus, it will be particular useful ...

Title:
Distributed Community Detection with the WCC Metric

Keywords:
community detection

Abstract:
<p>Community detection has become an extremely active area of research in recent ... this paper, we propose a new distributed, vertex-centric algorithm for community detection using the WCC metric. Results are presented that demonstrate the ...

References:
S.-H. Bae, D. Halperin, J. West, M. Rosvall, and B. Howe. Scalable flow-based community detection for large-scale network analysis. In Data Mining Workshops (ICDMW), 2013 IEEE 13th International Conference on, pages 303--310. IEEE, 2013.
S. Fortunato and M. Barthélemy. Resolution limit in community detection. PNAS, 104(1):36, 2007.
A. Lancichinetti. Community detection algorithms: a comparative analysis. Phy. Rev. E, 80(5):056117, 2009.
H. Lu, M. Halappanavar, and A. Kalyanaraman. Parallel heuristics for scalable community detection. arXiv preprint arXiv:1410.1237, 2014.
A. Prat-Pérez, D. Dominguez-Sal, and J.-L. Larriba-Pey. High quality, scalable and parallel community detection for large real graphs. In Proceedings of the 23rd International Conference on World Wide Web, WWW '14, pages 225--236, New York, NY, USA, 2014. ACM.
F. Radicchi. A paradox in community detection. EPL (Europhysics Letters), 106(3):38001, 2014.
J. Riedy, D. A. Bader, and H. Meyerhenke. Scalable multi-threaded community detection in social networks. In Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), 2012 IEEE 26th International, pages 1619--1628. IEEE, 2012.
J. Xie and B. Szymanski. Towards linear time overlapping community detection in social networks. In PAKDD, pages 25--36, 2012.
J. Yang and J. Leskovec. Overlapping community detection at scale: a nonnegative matrix factorization approach. In WSDM, pages 587--596, 2013.

Full Text:
Distributed Community Detection with the WCC MetricMatthew SaltzDAMA-UPCUniversitat Polit cnica deCatalunyamsaltz@ac.upc.eduArnau Prat-P rezDAMA-UPCUniversitat Polit cnica deCatalunyaaprat@ac.upc.eduDavid ... this paper, we propose a new dis-tributed, vertex-centric algorithm for community detection usingthe WCC metric. Results are presented that demonstrate the algo-rithm?s ... presenting an overview of related work in community detectionand distributed community detection. . Next, in Section 3, we intro-duce background material and ... a discussion of future work.2. RELATEDWORKMost of the research on community detection algorithms has fo-cused on single threaded algorithms on SMP machines. ... simulated annealing [13]. One of the mostfamous and widely used community detection algorithms based onmodularity maximization is the Louvain method [4], a ...
... Lancichinetti et al. [7], Infomap standsas one of the best community detection algorithms in the literature.Another category of algorithms is formed by ... are not well-defined.3. BACKGROUND & TERMINOLOGYInformally stated, the goal of community detection is, given agraph, to divide the graph into groups (communities) ...
... bar in each group indicates the runtimeof the centralized Scalable Community Detection algorithm from[18].centralized version reported in [18]. In Figure 3, we ...
... that value. For comparison, the average runtime of thecentralized Scalable Community Detection code was 5.56 hours.graph, with over 1.8 billion edges, the ... D. Halperin, J. West, M. Rosvall, and B. Howe.Scalable flow-based community detection for large-scalenetwork analysis. In Data Mining Workshops (ICDMW),2013 IEEE 13th ... Barth lemy. Resolution limit incommunity detection. PNAS, 104(1):36, 2007.[7] A. Lancichinetti. Community detection algorithms: acomparative analysis. Phy. Rev. E, 80(5):056117, 2009.[8] A. Lancichinetti, ... H. Lu, M. Halappanavar, and A. Kalyanaraman. Parallelheuristics for scalable community detection. . arXiv preprintarXiv:1410.1237, 2014.[12] G. Malewicz, M. H. Austern, A. ...
... Prat-P rez, D. Dominguez-Sal, and J.-L. Larriba-Pey.High quality, scalable and parallel community detection forlarge real graphs. In Proceedings of the 23rd InternationalConference on ... York, NY, USA, 2014. ACM.[19] F. Radicchi. A paradox in community detection. . EPL(Europhysics Letters), 106(3):38001, 2014.[20] U. N. Raghavan, R. Albert, ... 2007.[21] J. Riedy, D. A. Bader, and H. Meyerhenke. Scalablemulti-threaded community detection in social networks. InParallel and Distributed Processing Symposium Workshops& PhD ...

Title:
Local network community detection with continuous optimization of conductance and weighted kernel K-means

Keywords:
community detection

Abstract:
<p>Local network community detection is the task of finding a single community of nodes ... a popular objective function used in many algorithms for local community detection. . This paper studies a continuous relaxation of conductance. We ...

References:
Haim Avron and Lior Horesh. Community detection using time-dependent personalized pagerank. In Proceedings of The 32nd International Conference on Machine Learning, pages 1795-1803, 2015.
Santo Fortunato. Community detection in graphs. Physics Reports, 486:75-174, 2010.
Ullas Gargi, Wenjun Lu, Vahab S Mirrokni, and Sangho Yoon. Large-scale community detection on youtube for topic discovery and exploration. In ICWSM, 2011.
Kyle Kloster and David F. Gleich. Heat kernel based community detection. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '14, pages 1386-1395, New York, NY, USA, 2014. ACM. ISBN 978-1-4503-2956-9.
Andrea Lancichinetti, Santo Fortunato, and Filippo Radicchi. Benchmark graphs for testing community detection algorithms. Physical Review E, 78:046110, 2008.
Jure Leskovec, Kevin J Lang, and Michael Mahoney. Empirical comparison of algorithms for network community detection. In Proceedings of the 19th international conference on World wide web, pages 631-640. ACM, 2010.
Joyce Jiyoung Whang, David F Gleich, and Inderjit S Dhillon. Overlapping community detection using seed set expansion. In Proceedings of the 22nd ACM international conference on Conference on information & knowledge management, pages 2099-2108. ACM, 2013.
Yubao Wu, Ruoming Jin, Jing Li, and Xiang Zhang. Robust local community detection: On free rider effect and its elimination. Proc. VLDB Endow., 8(7):798-809, February 2015. ISSN 2150-8097.

Full Text:
... 17 (2016) 1-28 Submitted 1/16; Revised 6/16; Published 8/16Local Network Community Detection with ContinuousOptimization of Conductance and Weighted Kernel K-MeansTwan van Laarhoven ... University NijmegenPostbus 90106500 GL Nijmegen, The NetherlandsEditor: Jure LeskovecAbstractLocal network community detection is the task of finding a single community of nodesconcentrated ... is a popularobjective function used in many algorithms for local community detection. . This paperstudies a continuous relaxation of conductance. We show ... ground, while graph diffusion algorithms generate large communitiesof lower quality.1Keywords: community detection, , conductance, k-means1. IntroductionImagine that you are trying to find ... overallcommunity structure of a network has to be found, local community detection aims to findonly one community around the given seeds by ... local computations involvingonly nodes relatively close to the seed. Local community detection by seed expansion is1. Source code of the algorithms used ... et al., 2010; Wu et al., 2012).Several algorithms for local community detection operate by seed expansion. Thesemethods have different expansion strategies, but ... As a consequence, many heuris-tic and approximation algorithms for local community detection have been introduced (seereferences in the related work section). In ...
... that is, with k = 1. This relation leads2Local Network Community Detection with Continuous Optimizationto the introduction of a new objective function ... Optimizationto the introduction of a new objective function for local community detection, , called ?-conductance, which is the sum of conductance and ... and infor-mation science and biology has boosted research on network community detection (see forinstance the overviews by Schaeffer (2007) and Fortunato (2010)). ... and Its Local OptimizationConductance has been largely used for network community detection. . For instance Leskovecet al. (2008) introduced the notion of ...
... and Lang, 2006; Whang et al., 2013).Popular algorithms for local community detection employ the local graph diffusionmethod to find a community with ... seminal work by Spielman and Teng (2004) various algorithms forlocal community detection by seed expansion based on this approach have been proposed(Andersen ... (up to a logarithmic factor).Mahoney et al. (2012) performed local community detection by modifying the spectralprogram used in standard global spectral clustering. ... ObjectivesConductance is not the only objective function used in local community detection algo-rithms. Various other objective functions have been considered in the ... by its size, by replacing the denominator with the4Local Network Community Detection with Continuous Optimizationsum of weights of the community nodes, where ... CommunitiesInstead of focusing on objective functions and methods for local community detection, , otherresearchers investigated properties of communities. Mishra et al. (2008) ...
... vectors,which we could expand as?(c) = 1??i,j?V ciaijcj?i,j?V ciaij.6Local Network Community Detection with Continuous OptimizationWith this definition we can apply the vast ...
... This can be seen as a 2-means cluster assignment8Local Network Community Detection with Continuous Optimizationwhere the background cluster has the origin as ...
... this solution is projected so asto satisfy the constraints.10Local Network Community Detection with Continuous OptimizationIn our case, we start from an initial ... ? S5: t? t+ 16: while C(t) < C(t?1)12Local Network Community Detection with Continuous OptimizationThis leads us to the EM community finding ...
... descent algorithm from Section 3.1 we have an analogoustheorem,14Local Network Community Detection with Continuous OptimizationTheorem 5 If C? is dense and isolated, ... vector (Andersen et al., 2006). The values in this16Local Network Community Detection with Continuous Optimizationvector are divided by the degree of the ...
... |C?| ,2. The supplementary material is available from http://cs.ru.nl/~tvanlaarhoven/conductance201618Local Network Community Detection with Continuous OptimizationDataset PGDc-0 PGDc-d EMc-0 EMc-d YL HK PPRLFR ...
... smaller than the ground truth ones on these networks.20Local Network Community Detection with Continuous OptimizationDataset PGDc-0 PGDc-d EMc-0 EMc-d YL HK PPRLFR ...
... a very low clustering coefficient. In such a case,22Local Network Community Detection with Continuous Optimizationcommunities have many links to nodes outside, hence ... ?-conductance objective function and tosimple yet effective algorithms for local community detection by seed expansion.We provided a formalization of a class of ...
... Sym-posium on, pages 475?486. IEEE, 2006.Haim Avron and Lior Horesh. Community detection using time-dependent personalizedpagerank. In Proceedings of The 32nd International Conference ... The 32nd International Conference on Machine Learning,pages 1795?1803, 2015.24Local Network Community Detection with Continuous OptimizationShuchi Chawla, Robert Krauthgamer, Ravi Kumar, Yuval Rabani, ... Trans. Pattern Anal. Mach. Intell., 29(11):1944?1957,November 2007. ISSN 0162-8828.Santo Fortunato. Community detection in graphs. Physics Reports, 486:75?174, 2010.Ullas Gargi, Wenjun Lu, Vahab ... IEEE, 2011.Kyle Kloster and David F. Gleich. Heat kernel based community detection. . In Proceedingsof the 20th ACM SIGKDD International Conference on ...
... J Lang, and Michael Mahoney. Empirical comparison of algorithmsfor network community detection. . In Proceedings of the 19th international conference onWorld wide ... knit clusters in social networks. Internet Mathematics, 5(1):155?174, 2008.26Local Network Community Detection with Continuous OptimizationAlan Mislove, Bimal Viswanath, Krishna P. Gummadi, and ...

Title:
Community detection in social networks through similarity virtual networks

Keywords:
community detection

Abstract:
... networks. In this paper, we propose an approach to enhance community detection in online social networks using node similarity techniques. We apply ...

References:
Jonathan W. Berry, Bruce Hendrickson, Randall A. LaViolette, and Cynthia A. Phillips. Tolerating the community detection resolution limit with edge weighting. Proceedings of The National Academy of Sciences of the USA, 83(5): 056119, 2011.
Santo Fortunato. Community detection in graphs. Physics Reports, 486(3--5): 75--174, 2010.
Santo Fortunato and Marc Barthélemy. Resolution limit in community detection. Proceedings of The National Academy of Sciences of the USA, 104(1): 36--41, 2007.
Yoonseop Kang and Seungjin Choi. Common neighborhood sub-graph density as a similarity measure for community detection. Proceedings of the 16th International Conference on Neural Information Processing ICONIP 09, 1: 175--184, 2009.
Alireza Khadivi, Ali Ajdari Rad, and Martin Hasler. Community detection enhancement in networks using proper weighting and partial synchronization. Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), pages 3777--3780, 2010.
Alireza Khadivi, Ali Ajdari Rad, and Martin Hasler. Network community-detection enhancement by proper weighting. Physical Review E, 83(4): 046104, 2011.
Andrea Lancichinetti and Santo Fortunato. Community detection algorithms: A comparative analysis. Physical Review E, 80(5): 056117, Nov 2009.
Andrea Lancichinetti and Santo Fortunato. Limits of modularity maximization in community detection. Physical Review E, 84(6): 066122, Dec 2011.
Andrea Lancichinetti, Santo Fortunato, and Filippo Radicchi. Benchmark graphs for testing community detection algorithms. Physical Review E, 78(4): 046110, 2008.
Jure Leskovec, Kevin J. Lang, and Michael Mahoney. Empirical comparison of algorithms for network community detection. In Proceedings of the 19th international conference on World wide web, WWW '10, pages 631--640, New York, NY, USA, 2010. ACM.
Zhenping Li, Shihua Zhang, Rui-Sheng Wang, Xiang-Sun Zhang, and Luonan Chen. Quantitative function for community detection. Physical Review E, 77(3): 036109, 2008.
Pasquale De Meo, Emilio Ferrara, Giacomo Fiumara, and Alessandro Provetti. Enhancing community detection using a network weighting strategy. Information Sciences, 222: 648--668, 2013.
Farnaz Moradi, Tomas Olovsson, and Philippas Tsigas. An evaluation of community detection algorithms on large-scale email traffic. In Ralf Klasing, editor, SEA, volume 7276 of Lecture Notes in Computer Science, pages 283--294. Springer, 2012.
Günce Keziban Orman, Vincent Labatut, and Hocine Cherifi. Qualitative comparison of community detection algorithms. In Hocine Cherifi, Jasni Mohamad Zain, and Eyas El-Qawasmeh, editors, DICTAP (2), volume 167 of Communications in Computer and Information Science, pages 265--279. Springer, 2011.
Günce Keziban Orman, Vincent Labatut, and Hocine Cherifi. Comparative evaluation of community detection algorithms: A topological approach. CoRR, abs/1206.4987, 2012.
Symeon Papadopoulos, Yiannis Kompatsiaris, Athena Vakali, and Ploutarchos Spyridonos. Community detection in social media. Data Mining and Knowledge Discovery, 24: 515--554, 2012.
Carlos André Reis Pinheiro. Community detection to identify fraud events in telecommunications networks. In SAS SUGI Proceedings: Customer Intelligence. SAS Global Forum 2012, 2012.

Full Text:
... are proposinga pre-processing method that will prepare the social networkfor community detection algorithms. This preparation is shown4http://news.google.com/12013 IEEE/ACM International Conference on Advances ... In Section 3, we introduce and discuss our algorithmto enhance community detection. . Section 4 presents an experi-mental comparison of the proposed ... building communitiesof practice which gather professionals into common ?elds ofinterest. Community detection is also important to identifypowerful nodes in the network, based ...
... column is identi?ed as Nj .B. Related WorksMany algorithms for community detection have been pro-posed earlier [9], and extensive comparative studies betweenthese ... best of our knowledge, the use of weighting schemesto enhance community detection has been introduced in fewliteratures. Khadivi et al proposed the ...
... most k length. This approach was notdesigned for any speci?c community detection algorithm likein [16], [17]. Instead, it works with any algorithm ... International Conference on Advances in Social Networks Analysis and Mining1118III. COMMUNITY DETECTION MODELS AND ALGORITHMSIn this paper, we suggest a community detection proposal,which semantically enrich the network prior to proceed withthe community detection process, in order to enhance thisdiscovery process and deliver a ...
... shown in Table III. When ? = 0.4 and0.8, the communities detected by the Similarity CNM are 55%(a) Maximum Modularity When ? ...
... Bruce Hendrickson, Randall A. LaViolette, andCynthia A. Phillips. Tolerating the community detection resolution limitwith edge weighting. Proceedings of The National Academy of ... Journal of Statistical Mechanics:Theory and Experiment, 2005(9):P09008?09008, 2005.[9] Santo Fortunato. Community detection in graphs. Physics Reports,486(3-5):75 ? 174, 2010.[10] Santo Fortunato and ...
... Seungjin Choi. Common neighborhood sub-graphdensity as a similarity measure for community detection. . Proceedingsof the 16th International Conference on Neural Information ProcessingICONIP ... Physical Re-view E, 83(4):046104, 2011.[18] Andrea Lancichinetti and Santo Fortunato. Community detection algo-rithms: A comparative analysis. Physical Review E, 80(5):056117, Nov2009.[19] Andrea ... Andrea Lancichinetti and Santo Fortunato. Limits of modularity max-imization in community detection. . Physical Review E, 84(6):066122,Dec 2011.[20] Andrea Lancichinetti, Santo Fortunato, ... Lancichinetti, Santo Fortunato, and Filippo Radicchi. Bench-mark graphs for testing community detection algorithms. PhysicalReview E, 78(4):046110, 2008.[21] Jure Leskovec, Kevin J. Lang, ... Lang, and Michael Mahoney. Empirical com-parison of algorithms for network community detection. . In Proceedingsof the 19th international conference on World wide ... Zhang, Rui-Sheng Wang, Xiang-Sun Zhang, andLuonan Chen. Quantitative function for community detection. . PhysicalReview E, 77(3):036109, 2008.[23] Haralambos Marmanis and Dmitry Babenko. ... Pasquale De Meo, Emilio Ferrara, Giacomo Fiumara, and AlessandroProvetti. Enhancing community detection using a network weightingstrategy. Information Sciences, 222:648?668, 2013.[25] Farnaz Moradi, ... 2013.[25] Farnaz Moradi, Tomas Olovsson, and Philippas Tsigas. An evaluationof community detection algorithms on large-scale email traf?c. InRalf Klasing, editor, SEA, volume ... G nce Keziban Orman, Vincent Labatut, and Hocine Cheri?. Qualitativecomparison of community detection algorithms. In Hocine Cheri?,Jasni Mohamad Zain, and Eyas El-Qawasmeh, editors, ... Keziban Orman, Vincent Labatut, and Hocine Cheri?. Com-parative evaluation of community detection algorithms: A topologicalapproach. CoRR, abs/1206.4987, 2012.[30] Symeon Papadopoulos, Yiannis Kompatsiaris, ... abs/1206.4987, 2012.[30] Symeon Papadopoulos, Yiannis Kompatsiaris, Athena Vakali, andPloutarchos Spyridonos. Community detection in social media. DataMining and Knowledge Discovery, 24:515?554, 2012.[31] Carlos ... DataMining and Knowledge Discovery, 24:515?554, 2012.[31] Carlos Andr Reis Pinheiro. Community detection to identify fraudevents in telecommunications networks. In SAS SUGI Proceedings:Customer ...

Keywords:
community detection

Full Text:
... usersdoes not give any significant advantage to the performanceof the community detection algorithms. This is due to thefact that the similarity matrices ...

Title:
Modularity approach for community detection in complex networks

Keywords:
community detection

Abstract:
<p>Community detection has been one of the relevant areas in the field ... large graph with over millions of vertices and edges. Different community detection algorithms have been proposed in different perspective of almost similar ...

References:
Fortunato, S. Community detection in graphs. Physics Reports, 486(3--5): 75--174, 2010.
Yang J and Leskovec J. Community-Affiliation Graph Model for Overlapping Network Community Detection. In ICDM, 2012.
Lancichinetti A and Fortunato S. Community detection algorithms: a comparative analysis. Phys. Rev., E 80: 056117, 2009.

Full Text:
Proceedings Template - WORDModularity Approach for Community Detection in Complex Networks Suriana Ismail Universiti Kuala Lumpur Malaysian Institute ... Information Technology Jalan Sultan Ismail, Kuala Lumpur, Malaysia drroslan@unikl.edu.my ABSTRACT Community detection has been one of the relevant areas in the field ... large graph with over millions of vertices and edges. Different community detection algorithms have been proposed in different perspective of almost similar ... phylogenetic studies. CCS Concepts ? Applied computing??Biological networks Keywords Modularity, community detection, , complex networks. 1. INTRODUCTION In recent years, a large ... community have been published in the literature. Research interest in community detection in particular evolved from a wide range of real ?world ... huge and complex network existence, it imposed another perspective of community detection problem. Thus, detecting community structure is important in order to ...
... the algorithm approach to detect communities. 2. BACKGROUND STUDY 2.1 Community Detection approaches Many work has been focused on discovering communities in ... between its members than with the rest of the network. Community detection has been center of interest for researcher since the prominent ... to be applied to any type of network. Thus, the community detection algorithm aims to find similar node in a group and ...
... user to input number of OTUs [17]. The goal of community detection is to identify sets of nodes with common function based ... connected by a set of m edges E={???=(??,???)}. Algorithm I: Community Detection General Notation: A node represents a sequence of gene. An ...
... human gut bacteria sequence. To evaluate the performance of the community detection algorithm approach, we use the available dataset as depicted in ... In this section, experimental study with all dataset on the community detection based on modularity optimization approach has been executed. The following ... for helpful comments and suggestion. 8. REFERENCES [1] Fortunato, S. Community detection in graphs. Physics Reports, 486(3-5): 75-174, 2010. [2] Girvan M ... J and Leskovec J. Community-Affiliation Graph Model for Overlapping Network Community Detection. . In ICDM, 2012. [7] Yang J and Leskovec J. ... 0.724 0.722 0.631 0.707 [13] Lancichinetti A and Fortunato S. Community detection algorithms: a comparative analysis. Phys. Rev., E 80: 056117, 2009. ...

Keywords:
community detection

Abstract:
... Mining. Specifically in clustering tasks, these models allow to use community detection algorithms in networks in order to detect data clusters. In ... clustering detection algorithms based on relational data using measures for community detection in networks. We carried out an exploratory analysis over 23 ...

References:
T. B. S. de Oliveira, L. Zhao, K. Faceli, and A. C. P. L. F. de Carvalho. Data clustering based on complex network community detection. In IEEE Congress on Evolutionary Computation, pages 2121--2126, 2008.
C. Granell, S. Gómez, and A. Arenas. Data clustering using community detection algorithms. Int. J. of Complex Systems in Science, 1:21--24, 2011.
A. Lancichinetti and S. Fortunato. Community Detection Algorithms: A Comparative Analysis. Phys. Rev. E, 80(5):056117+, 2009.
J. Leskovec, K. J. Lang, and M. Mahoney. Empirical comparison of algorithms for network community detection. In Proc. of 19th Int. Conf. on World wide web, WWW '10, pages 631--640, USA, 2010. ACM.
G. K. Orman, V. Labatut, and H. Cherifi. Qualitative comparison of community detection algorithms. CoRR, abs/1207.3603, 2012.
Z. Ye, S. Hu, and J. Yu. Adaptive clustering algorithm for community detection in complex networks. Phys. Rev. E, 78(4):046115, 2008.

Full Text:
... Data Mining. Specifically in clustering tasks,these models allow to use community detection algorithmsin networks in order to detect data clusters. In this ... with clustering detection algorithms based onrelational data using measures for community detection innetworks. We carried out an exploratory analysis over 23 nu-merical ... of highly connected examples separatedby a few edges, so that community detection methods canbe successfully applied to identify relevant clusters.150Recent progress in ... in the analysis of social networks broughtabout new algorithms for community detection, , which alsocould have some potential for the clustering of ...
... discussed in business, engineering, sci-ence, medicine and entertainment.As far as community detection in networks is concerned,relevant contributions are distinguished mainly by analysingnetworks ... analysingnetworks with di?erent attributes. Danon et al. [3] com-pared 16 community detection methods on artificial datasets, analyzing the precision and computational cost, ... biases in the clusters identified. Orman et al. [21]applied five community detection methods on artificial net-works with real-world network properties, analysing theirprecision.Nonetheless, ...
... complete weighted graph and a multi-resolution scheme[5] is employed for community detection. . The method wasapplied solely over the Iris dataset, and ...
... low com-putational cost as compared to other methods (O nlog2n ).Community detection algorithms may adopt the modular-ity Q to establish the ideal ... 5, 7 and 11. For each net-work, we employed the community detection methods FastGreedy [20] and Adaptive Clustering [27], and the modu-larity ...
... C. P.L. F. de Carvalho. Data clustering based on complexnetwork community detection. . In IEEE Congress onEvolutionary Computation, pages 2121?2126, 2008.[5] S. ... 2009.[6] C. Granell, S. Go mez, and A. Arenas. Data clusteringusing community detection algorithms. Int. J. ofComplex Systems in Science, 1:21?24, 2011.[7] L. ... G. K. Orman, V. Labatut, and H. Cherifi. Qualitativecomparison of community detection algorithms.CoRR, abs/1207.3603, 2012.[22] W. M. Rand. Objective Criteria for the ...
... Z. Ye, S. Hu, and J. Yu. Adaptive clustering algorithmfor community detection in complex networks. Phys.Rev. E, 78(4):046115, 2008.[28] Y. Zhao and ...

Keywords:
community detection

References:
I. Psorakis, S. Roberts, M. Ebden, and B. Sheldon. Overlapping community detection using bayesian non-negative matrix factorization. Physical Review E, 83(6):066114, 2011.

Title:
Community Detection based on Distance Dynamics

Keywords:
community detection

Abstract:
<p>In this paper, we introduce a new community detection algorithm, called Attractor, which automatically spots communities in a network ... experiments show that our algorithm allows the effective and efficient community detection

References:
Santo Fortunato. Community detection in graphs. Physics Reports, 486(3):75--174, 2010.
Santo Fortunato and Marc Barthélemy. Resolution limit in community detection. PNAS, 104(1):36--41, 2007.
Andrea Lancichinetti, Santo Fortunato, and Filippo Radicchi. Benchmark graphs for testing community detection algorithms. Physical review E, 78(4):046110, 2008.

Full Text:
... pinpointed. Extensiveexperiments show that our algorithm allows the effectiveand efficient community detection and has good performancecompared to state-of-the-art algorithms.KeywordsCommunity detection; Interaction model; ... state-of-the-art algorithms.KeywordsCommunity detection; Interaction model; Network1. INTRODUCTIONDuring the past decades, community detection [3] (alsocalled graph clustering or graph partitioning) has attractedPermission to ... date.In this paper, instead of introducing a new user-definedcriterion for community detection like normalized cut [16]or modularity [11], we consider the problem ...
... (b) Intermediate State (c) Steady StateFigure 1: The illustration of community detection based on distance dynamics. (a) A social network, wherethe dashed ... simulating the distance dynamics, Attractor has sev-eral attractive benefits for community detection in networks,most importantly:? Intuitive Community Detection: : Instead of opti-mizing user-specified measures, Attractor investigatesthe community structure ... WORKDuring the past several decades, many approaches havebeen established for community detection, , such as [8], [16],[15] [11] etc. Due to space ...
[14][3].Cut-Criteria Based Community Detection. . Thecut-criterion based community detection algorithms refer toa class of widely used techniques which seek ... of uncovering the high-quality communities, but alsoallows handling large-scale networks.3. COMMUNITY DETECTION BASED ONDISTANCE DYNAMICS3.1 Distance Dynamics versus User-defined C-ommunity CriteriaCurrently, many ... thisstudy, instead of introducing new user-defined criterion, wepresent a new community detection approach based on thedistance dynamics. As stated in Section 1.1, ...
... its time complexity in Section 3.5.3.2 PreliminariesFor the purpose of community detection, , some necessarydefinitions are first introduced.Definition 1 (Undirected Graph ) ...
... fraction of communities is usually small [1].However, for many traditional community detection algo-rithms, such as Modularity or Ncut, they tend to partitionthe ... theperformance of Attractor, we compare it to several repre-sentatives of community detection algorithms.Ncut [16] is a well-known algorithm for graph clusteringby optimizing ...
... hierarchical community detec-tion and has lower time complexity.Infomap [13] envisions community detection problem asa coding problem, and aims at finding the optimal ... net-works featuring distinct characteristics to compare the per-formance of various community detection algorithms. Forfair comparison and to make the synthetic networks to ...
... World DataIn this section, we evaluate the performances of differ-ent community detection algorithms on real-world networkswhich are all publicly available from the ...
... of resulting communities.5. CONCLUSIONSIn this paper, we introduce a new community detection al-gorithm, called Attractor, to automatically uncover commu-nity structure in networks ... networks. Journal of StatisticalMechanics: Theory and Experiment, 2008(10):P10008,2008.[3] Santo Fortunato. Community detection in graphs.Physics Reports, 486(3):75?174, 2010.[4] Santo Fortunato and Marc Barthe lemy. ... Reports, 486(3):75?174, 2010.[4] Santo Fortunato and Marc Barthe lemy. Resolutionlimit in community detection. . PNAS, 104(1):36?41,2007.[5] Michelle Girvan and Mark EJ Newman. Communitystructure ...

Title:
Overlapping community detection in networks: The state-of-the-art and comparative study

Keywords:
Overlapping community detection

Abstract:
<p>This article reviews the state-of-the-art in <i>overlapping</i> community detection algorithms, quality measures, and benchmarks. A thorough comparison of different ...

References:
Ding, F., Luo, Z., Shi, J., and Fang, X. 2010. Overlapping community detection by kernel-based fuzzy affinity propagation. In Proceedings of the International Workshop on Indoor Spatial Awareness (ISA'10). 1--4.
Fortunato, S. 2010. Community detection in graphs. Phys. Rep. 486, 75--174.
Gregory, S. 2009. Finding overlapping communities using disjoint community detection algorithms. CompleNet 207, 47--61.
Lancichinetti, A. and Fortunato, S. 2009. Community detection algorithms: A comparative analysis. Phys. Rev. E 80, 5.
Lancichinetti, A., Fortunato, S., and Radicchi, F. 2008. Benchmark graphs for testing community detection algorithms. Phys. Rev. E 78, 4.
Leskovec, J., Lang, K. J., and Mahoney, M. W. 2010. Empirical comparison of algorithms for network community detection. In Proceedings of the 19^th Conference on World Wide Web (WWW'10). 631--640.
Psorakis, I., Roberts, S., Ebden, M., and Sheldon, B. 2011. Overlapping community detection using bayesian non-negative matrix factorization. Phys. Rev. E 83, 6.
Rees, B. and Gallagher, K. 2010. Overlapping community detection by collective friendship group inference. In Proceedings of the International Conference on Advances in Social Network Analysis and Mining (ASONAM'10). 375--379.
Reichardt., J. and Bornholdt, S. 2006a. Statistical mechanics of community detection. Phys. Rev. E 74, 1.
Ronhovde, P. and Nussinov, Z. 2009. Multiresolution community detection for megascale networks by information-based replica correlations. Phys. Rev. E 80, 1.
Wang, X., Jiao, L., and Wu, J. 2009. Adjusting from disjoint to overlapping community detection of complex networks. Physica A388, 5045--5056.
Wu, Z., Lin, Y., Wan, H., and Tian, S. 2010. A fast and reasonable method for community detection with adjustable extent of overlapping. In Proceedings of the Conference on Intelligent Systems and Knowledge Engineering (ISKE'10). 376--379.
Xie, J. and Szymanski, B. K. 2011. Community detection using a neighborhood strength driven label propagation algorithm. In Proceedings of the IEEE Network Science Workshop (NSW'11). 188--195.
Xie, J. and Szymanski, B. K. 2012. Towards linear time overlapping community detection in social networks. In Proceedings of the 16^th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining (PAKDD'12). 25--36.
Zhang, Y., Wang, J., Wang, Y., and Zhou, L. 2009. Parallel community detection on large networks with propinquity dynamics. In Proceedings of the 15^th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD'09). 997--1006.

Full Text:
CSUR4504-4343Overlapping Community Detection in Networks: The State-of-the-Artand Comparative StudyJIERUI XIE, Rensselaer Polytechnic InstituteSTEPHEN ... SZYMANSKI, Rensselaer Polytechnic InstituteThis article reviews the state-of-the-art in overlapping community detection algorithms, quality measures,and benchmarks. A thorough comparison of different algorithms ... and networksGeneral Terms: Algorithms, PerformanceAdditional Key Words and Phrases: Overlapping community detection, , social networksACM Reference Format:Xie, J., Kelley, S., and Szymanski, ... Format:Xie, J., Kelley, S., and Szymanski, B. K. 2013. Overlapping community detection in networks: The state-of-the-art and comparative study. ACM Comput. Surv. ... community, numerous techniques have been developedfor both efficient and effective community detection. . Random walks, spectral clustering,modularity maximization, differential equations, and statistical ... mechanics have allbeen used previously. Much of the focus within community detection has been onidentifying disjoint communities. This type of detection assumes ... to the rest of the network. Recent reviews on disjoint community detection arepresented in Danon et al. [2005], Lancichinetti and Fortunato [2009], ...
... social networks.For this reason, there is growing interest in overlapping community detection algo-rithms that identify a set of clusters that are not ... connection between nodes i and j.In the case of overlapping community detection, , the set of clusters found is called acover C ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:3crisp assignment, the relationship between a node and ... output crisp community assignments.3. ALGORITHMSIn this section, algorithms for overlapping community detection are reviewed andcategorized into five classes which reflect how communities ...
... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:5The proposed density function can be formally given ...
... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:7merged. The optimal cut on the dendrogram is ... 1989] or O(n3) for a dense enough graph.3.4. Fuzzy DetectionFuzzy community detection algorithms quantify the strength of association betweenall pairs of nodes ... or calculated fromthe data.Nepusz et al. [2008] modeled the overlapping community detection as a nonlin-ear constrained optimization problem which can be solved ...
... probabilistic nature, mixture models provide an appropriate frame-work for overlapping community detection [Newman and Leicht 2007]. In general, thenumber of mixture models ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:9Similar mixture models can also be constructed as ...
... is assigned to each node, can also be applied to community detection. . One of suchmodels is the q-state Potts model [Blatt ... a spin may take, indicating the maximum numberof communities. The community detection problem is equivalent to the problem of11http://www.cs.bris.ac.uk/~steve/networks/software/copra.html.12https://sites.google.com/site/communitydetectionslpa.ACM Computing Surveys, Vol. ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:11minimizing the Hamiltonian of the model. In the ...
... from disjoint to overlapping communities is rarely straightfor-ward. Unlike disjoint community detection, , where a number of measures have beenproposed for comparing ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:13considers how many pairs of nodes belong together ...
... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:15from the range [1,10]. For SLPA, parameter r ...
... especially the mixing value ?, have asimilar impact for disjoint community detection. . That is, the larger the value of ?, thepoorer ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:19Fig. 4. Evaluations of overlapping community detection on LFR networks with high overlap density On =50%. Left ...
... Publication date: August 2013.43:20 J. Xie et al.Table II. The Community Detection Ranking for n= 5000, ? = 0.3 and Low OverlappingDensity ... iLCD CIS14 UEOC UEOC iLCD UEOC UEOC NMFTable III. The Community Detection Ranking for n= 5000, ? = 0.3 and HighOverlapping Density ... rankings, we further derive the average ranking RS?NMI,Omegaas the overall community detection performance. In this final ranking, the top sevenalgorithms are exclusively ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:21Fig. 5. Histogram of the detected community sizes ...
... nodes, although often neglected, is essential forassessing the accuracy of community detection algorithms. Measures like NMI andOmega focus only on providing an ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:23where recall is the number of correctly detected ...
... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:25Fig. 9. Evaluations of overlapping node detection on ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:27Table V. The Overlapping Node DetectionRanking for n= ...
... inefficiency in large networks. As areference, we also performed disjoint community detection with the Infomap algorithm[Rosvall 2008], which has been shown quite ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:29Fig. 12. Overlapping modularity QEov for social networks.Fig. ...
... DISCUSSIONSIn this article, we review a wide range of overlapping community detection algorithmsalong with quality measures and several existing benchmarks. A number ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:31of agreement of different algorithms is the relatively ... structures has been previously explored only withinthe context of disjoint community detection and based on the notion of modularity[Reichardt and Bornholdt 2006b; ...
... F., LUO, Z., SHI, J., AND FANG, X. 2010. Overlapping community detection by kernel-based fuzzy affinitypropagation. In Proceedings of the International Workshop ... a graph. J. Graph Theor. 13, 4, 505?512.FORTUNATO, S. 2010. Community detection in graphs. Phys. Rep. 486, 75?174.FREY, B. J. AND DUECK, ...
... 5211, Springer, 408?423.GREGORY, S. 2009. Finding overlapping communities using disjoint community detection algorithms. Com-pleNet 207, 47?61.GREGORY, S. 2010. Finding overlapping communities in ... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:33GUIMERA, R., SALES-PARDO, M., AND AMARAL, L. A. ... percolation.Phys. Rev. E 78, 2.LANCICHINETTI, A. AND FORTUNATO, S. 2009. Community detection algorithms: A comparative analysis. Phys.Rev. E 80, 5.LANCICHINETTI, A., FORTUNATO, ...
... I., ROBERTS, S., EBDEN, M., AND SHELDON, B. 2011. Overlapping community detection using bayesiannon-negative matrix factorization. Phys. Rev. E 83, 6.RAGHAVAN, U. ... Rev. E 76, 3.REES, B. AND GALLAGHER, K. 2010. Overlapping community detection by collective friendship group inference.In Proceedings of the International Conference ... 93, 2.REICHARDT., J. AND BORNHOLDT, S. 2006a. Statistical mechanics of community detection. . Phys. Rev. E 74, 1.REICHARDT, J. AND BORNHOLDT, S. ... J. 6, 1, 50?57.RONHOVDE, P. AND NUSSINOV, Z. 2009. Multiresolution community detection for megascale networks byinformation-based replica correlations. Phys. Rev. E 80, ... L., AND WU, J. 2009. Adjusting from disjoint to overlapping community detection of complexnetworks. Physica A388, 5045?5056.WHITE, S. AND SMYTH, P. 2005. ...
... Vol. 45, No. 4, Article 43, Publication date: August 2013.Overlapping Community Detection in Networks 43:35WU, Z., LIN, Y., WAN, H., AND TIAN, ... AND TIAN, S. 2010. A fast and reasonable method for community detection withadjustable extent of overlapping. In Proceedings of the Conference on ... and KnowledgeEngineering (ISKE?10). 376?379.XIE, J. AND SZYMANSKI, B. K. 2011. Community detection using a neighborhood strength driven label propa-gation algorithm. In Proceedings ... J. AND SZYMANSKI, B. K. 2012. Towards linear time overlapping community detection in social networks.In Proceedings of the 16th Pacific-Asia Conference on ... Y., WANG, J., WANG, Y., AND ZHOU, L. 2009. Parallel community detection on large networks withpropinquity dynamics. In Proceedings of the 15th ...

Keywords:
Twitter, Social Networks, Community Detection

Abstract:
Many community detection algorithms have been developed to detect communities on Online Social ...

References:
N. Du, B. Wu, X. Pei, B. Wang, and L. Xu, "Community detection in large-scale social networks," in Proc. of Web KDD/SNA-KDD'07, pp. 16-25.
S. Fortunato, "Community detection in graphs," Physics Reports, vol. 486, no. 3-5, pp. 75-174, 2010.

Full Text:
... EngineeringThe University of Western AustraliaCrawley, WA 6009, AustraliaEmail: kwanhui@graduate.uwa.edu.au, datta@csse.uwa.edu.auAbstract?Many community detection algorithms have beendeveloped to detect communities on Online Social Networks(OSN). ... matching [1]and the connectedness of this group facilitates word-of-mouthadvertising [2].Most community detection algorithms consider only topo-logical information (such as follower/following links) but ... to consider user activity in addition to topo-logical information for community detection, , especially foradvertising and marketing purposes. We propose a method ...
... users with morethan 10,000 followers.We extend upon the Common Interest Community Detection( (CICD) method [19], [20] which is used for detecting com-munities ...
... the results obtained byour proposed methods are independent of the community detection algorithmchosen. CPM was chosen due to its ability to detect ... the common interest. Due to this differentusage of links, the communities detected by the CICD andHICD methods may overlap but are unlikely ... - CPMComHICD - CPMComCICD - InfomapComHICD - InfomapFig. 1. Total communities detected 1 10 100 1000Country MusicTennisMavericksBullsNo. of NodesComCICD - CPMComHICD - ...
... are shown in Fig. 1 and 2 respectively.The number of communities detected by our HICD methodis dependent on the duration of the ... Alonger period of tweet collection results in a larger numberof communities detected, , as there is a higher probability ofusers @mentioning each ... was used, Fig. 2 shows a similartrend in the largest community detected (e.g. communitiesdetected by CPM are larger than that by Infomap ...
... Du, B. Wu, X. Pei, B. Wang, and L. Xu, ?Community detection inlarge-scale social networks,? in Proc. of WebKDD/SNA-KDD ?07, pp.16?25.[19] K. ... Sciences, vol. 105, no. 4, pp. 1118?1123, 2008.[23] S. Fortunato, ?Community detection in graphs,? Physics Reports, vol.486, no. 3-5, pp. 75?174, 2010.[24] ...

Keywords:
community detection

References:
M. Kewalramani. Community Detection in Twitter. Master's thesis, May 2011.
Santo and Fortunato. Community detection in graphs. Physics Reports, 486:75--174, 2010.
T. Yang, R. Jin, Y. Chi, and S. Zhu. Combining link and content for community detection: a discriminative approach. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD '09, pages 927--936, New York, NY, USA, 2009. ACM.

Full Text:
... isa significant characteristic of any social network. Commu-nity discovery or Community detection in social networkshas many practical applications and hence, is of ...
... like Digital Marketing and LawEnforcement Agencies.3. RELATEDWORKOver the past decade, community detection has attractedresearch attention all over the world. Various algorithmshave been ... Santoand Fortunato have performed an in-depth survey in theproblem of community detection in graphs [20]. Tscher-teu and Langreiter propose a heuristic based ...
the complete graphto be loaded into memory for community detection [16, 19,27]. iTop snowballs from a true-positive seed on a ... disputed regionin the northern part of India).2. Investigation of a community detection algorithm re-lying on local information to infer topic-centric com-munity structures ...
... ?03, pages 137?146, NewYork, NY, USA, 2003. ACM.[8] M. Kewalramani. Community Detection in Twitter. Master?sthesis, May 2011.[9] R. Kumar, P. Raghavan, S. ... 331?340, New York, NY, USA, 2012. ACM.[20] Santo and Fortunato. Community detection in graphs. PhysicsReports, 486:75 ? 174, 2010.[21] A. Sureka, P. ...
... Jin, Y. Chi, and S. Zhu. Combining link andcontent for community detection: : a discriminative approach. InProceedings of the 15th ACM SIGKDD ...

Title:
Privacy preserving social graphs for high precision community detection

Keywords:
community detection

Abstract:
... a social network requires publishing the social network's data. However, community detection from raw data of a social network may reveal many ... resolve this issue, we address the problem of privacy preserving community detection ... in social networks. More specifically, we want to ensure that community detection is possible from the published social graph/data but the identity ...

References:
H. Dev, M. E. Ali, and T. Hashem. User interaction based community detection in online social networks. In Database Systems for Advanced Applications, volume 8422, pages 296--310. 2014.

Full Text:
... detection in social networks. More specifically, we wantto ensure that community detection is possible from the pub-lished social graph/data but the identity ... disclosed.Categories and Subject DescriptorsH.2.8 [Database Management]: Database Applications?Data MiningKeywordsSocial Networks, Community Detection, , Privacy1. PROBLEM FORMULATIONCommunity Detection: The community detection in asocial graph G(V,E) involves grouping vertices into clustersC = ... V thatare closely related, and hence forms a community.Privacy Preserving Community Detection: : Our ob-jective is to detect original communities from the ... graph modification approaches fail to serve ourpurpose of high precision community detection from privacypreserving social graphs.3. METHODOLOGYOur solution is based on a ... the original social graph whichis highly accurate in terms of community detection queries.In particular, we greedily modify the original social graphfocusing on ...
... H. Dev, M. E. Ali, and T. Hashem. User interactionbased community detection in online social networks.In Database Systems for Advanced Applications, volume8422, ...