526 Hits in 4.0 sec

Quadratic Optimization based Clique Expansion for Overlapping Community Detection [article]

Yanhao Yang, Pan Shi, Yuyi Wang, Kun He
2020 arXiv   pre-print
In this work, we present the QOCE (Quadratic Optimization based Clique Expansion), an overlapping community detection algorithm that could scale to large networks with hundreds of thousands of nodes and  ...  QOCE follows the popular seed set expansion strategy, regarding each high-quality maximal clique as the initial seed set and applying quadratic optimization for the expansion.  ...  Conclusion In this paper, we developed a new seed set expansion method called Quadratic Optimization based Clique Expansion (QOCE) for the overlapping community detection problem.  ... 
arXiv:2011.01640v1 fatcat:rpnbpzflbfby7k6i7i76ubqmvq

Disjoint and Non-Disjoint Community Detection with Control of Overlaps Between Communities

Chiheb-Eddine Ben NCir, Ismail Maiza, Waad Bouaguel, Nadia Essoussi
2021 SN Computer Science  
The regulation of overlaps is introduced in the objective criterion and optimized iteratively during the community detection process.  ...  To solve these issues, we propose a novel non-disjoint community detection method, referred to as CDCO, which easily allows users to interact with the system and regulate overlaps between communities based  ...  These steps must be repeated for each node v i in the network to build the partitioning matrix C.  ... 
doi:10.1007/s42979-020-00391-w fatcat:ixevvxqy35eqpmwfriw6ads3ku

Detecting Highly Overlapping Communities with Model-Based Overlapping Seed Expansion

Aaron McDaid, Neil Hurley
2010 2010 International Conference on Advances in Social Networks Analysis and Mining  
As research into community finding in social networks progresses, there is a need for algorithms capable of detecting overlapping community structure.  ...  In this paper we present a scalable algorithm, MOSES, based on a statistical model of community structure, which is capable of detecting highly overlapping community structure, especially when there is  ...  INTRODUCTION In this paper we introduce MOSES, a Model-based Overlapping Seed ExpanSion 1 algorithm, for finding overlapping communities in a graph.  ... 
doi:10.1109/asonam.2010.77 dblp:conf/asunam/McDaidH10 fatcat:hx4g4m33yrdp7gszaperccpcym

Static and Dynamic Community Detection Methods that Optimize a Specific Objective Function: A Survey and Experimental Evaluation

Kamal Taha
2020 IEEE Access  
We survey in this paper all fine-grained community detection categories, the clustering methods that fall under these categories, and the techniques employed by these methods for optimizing each objective  ...  We provide methodology-based taxonomies that classify static and dynamic community detection methods into hierarchically nested, fine-grained, and specific classes.  ...  [134] proposed a bottom-up intermediary seed expansion method for detecting overlapping communities.  ... 
doi:10.1109/access.2020.2996595 fatcat:lf6ghd6afjhi7cls4vnutoytlu

Using Model-based Overlapping Seed Expansion to detect highly overlapping community structure [article]

Aaron F. McDaid, Neil J. Hurley
2010 arXiv   pre-print
As research into community finding in social networks progresses, there is a need for algorithms capable of detecting overlapping community structure.  ...  In this paper we present a scalable algorithm, MOSES, based on a statistical model of community structure, which is capable of detecting highly overlapping community structure, especially when there is  ...  Brendan Murphy for providing feedback on the MOSES model.  ... 
arXiv:1011.1970v3 fatcat:nty2eth2ibfv7mrfr7mpja3sdq

A classification for community discovery methods in complex networks

Michele Coscia, Fosca Giannotti, Dino Pedreschi
2011 Statistical analysis and data mining  
The aim of this survey is to provide a manual for the community discovery problem.  ...  Given a meta definition of what a community in a social network is, our aim is to organize the main categories of community discovery based on their own definition of community.  ...  ACKNOWLEDGMENTS We gratefully acknowledge Sune Lehmann for useful discussions.  ... 
doi:10.1002/sam.10133 fatcat:vyy377nwdnc7pigfpiqfx7x3eq

Percolation Computation in Complex Networks [article]

Fergal Reid, Aaron McDaid, Neil Hurley
2012 arXiv   pre-print
Our approaches perform much better than existing algorithms on networks exhibiting pervasively overlapping community structure, especially for higher values of k.  ...  K-clique percolation is an overlapping community finding algorithm which extracts particular structures, comprised of overlapping cliques, from complex networks.  ...  [1] is k-clique percolation, which Fortunato's review [2] of community detection methods describes as the most popular overlapping community detection method.  ... 
arXiv:1205.0038v1 fatcat:juapoebuknei7hzy5pfseaaooq

High-order Line Graphs of Non-uniform Hypergraphs: Algorithms, Applications, and Experimental Analysis [article]

Xu T. Liu, Jesun Firoz, Sinan Aksoy, Ilya Amburg, Andrew Lumsdaine, Cliff Joslyn, Assefaw H. Gebremedhin, Brenda Praggastis
2022 arXiv   pre-print
Our results focus on the edge-based s-line graph expansion, but the methods we develop work for higher-order clique expansions as well.  ...  Much of the current analysis of hypergraphs relies on first performing a graph expansion – either based on the nodes (clique expansion), or on the edges (line graph) – and then running standard graph analytics  ...  For these curated datasets, in particular, each hypergraph, constructed from the social network datasets such as com-Orkut and Friendster in Table IV , are materialized by running a community detection  ... 
arXiv:2201.11326v1 fatcat:hjyufxso3rdvtfmkhz75mapb7i

Tradeoffs between density and size in extracting dense subgraphs: A unified framework

Zhefeng Wang, Lingyang Chu, Jian Pei, Abdullah Al-Barakati, Enhong Chen
2016 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)  
Third, we develop an efficient quadratic programming method for the unified framework, which is a generalization and extension to the existing methods.  ...  We show that optimizing the unified framework is essentially a relaxation of the maximization of a family of density functions. Last, we report a systematic empirical study to verify our findings.  ...  For example, in social networks, a dense subgraph may correspond to a closely connected community [1] , [2] , [3] .  ... 
doi:10.1109/asonam.2016.7752211 dblp:conf/asunam/WangCPAC16 fatcat:bvt2givdczegvpbvi7t2vveege

Fuzzy overlapping communities in networks

Steve Gregory
2011 Journal of Statistical Mechanics: Theory and Experiment  
We find that it has a strong effect on the performance of community detection methods: some algorithms perform better with fuzzy overlapping while others favour crisp overlapping.  ...  Often these communities overlap, such that each vertex may occur in more than one community.  ...  Acknowledgements I am grateful to Tamás Nepusz and Giuseppe Mangioni for discussions on fuzzy overlapping, and to them, Conrad Lee, and the anonymous referees for comments on a draft of this paper.  ... 
doi:10.1088/1742-5468/2011/02/p02017 fatcat:pq7k7n3h4jfndabxu2omxxisdi

Local Network Community Detection with Continuous Optimization of Conductance and Weighted Kernel K-Means [article]

Twan van Laarhoven, Elena Marchiori
2016 arXiv   pre-print
Conductance is a popular objective function used in many algorithms for local community detection. This paper studies a continuous relaxation of conductance.  ...  Experiments are conducted on networks with ground-truth communities, comparing to state-of-the-art graph diffusion algorithms for conductance optimization.  ...  Acknowledgments We thank the reviewers for their useful comments.  ... 
arXiv:1601.05775v2 fatcat:q7bcazup7rdehoreohbuvfwvwy

Applications of a Graph Theoretic Based Clustering Framework in Computer Vision and Pattern Recognition [article]

Yonatan Tariku Tesfaye
2018 arXiv   pre-print
We proposed novel approaches to solve multi-target tracking, visual geo-localization and outlier detection problems using a unified underlining clustering framework, i.e., dominant set clustering and its  ...  Acknowledgments First and for most, I thank Jehovah God for everything he has done for me.  ...  The approach is based on a parametrized family of quadratic programs that generalizes the standard quadratic optimization problem.  ... 
arXiv:1802.02181v1 fatcat:snsch56pdjglro2h32lhh5r64e

Quadratic Program-Based Modularity Maximization for Fuzzy Community Detection in Social Networks

Jianhai Su, Timothy C. Havens
2015 IEEE transactions on fuzzy systems  
In this paper, we present the Fuzzy Modularity Maximization (FMM) approach for community detection, which finds overlapping-that is, fuzzycommunities (where appropriate) by maximizing a generalized form  ...  One of the most important elements of social network analysis is community detection: i.e., finding groups of similar people based on their traits.  ...  [14] categorized overlapping community detection methods into five groups: clique percolation, link partitioning, local expansion and optimization, fuzzy detection, and agentbased and dynamical algorithms  ... 
doi:10.1109/tfuzz.2014.2360723 fatcat:ohwwbty6fvhmtbxdybct4jb7oa

Overlapping Community Detection via Local Spectral Clustering [article]

Yixuan Li, Kun He, David Bindel, John Hopcroft
2015 arXiv   pre-print
In this paper, we propose a novel approach for finding overlapping communities called LEMON (Local Expansion via Minimum One Norm).  ...  Moreover, given that networks are not all similar in nature, a comprehensive analysis on how the local expansion approach is suited for uncovering communities in different networks is still lacking.  ...  Acknowledgement The first author would like to thank Kyle Kloster for the comments on the earlier conference proceeding version.  ... 
arXiv:1509.07996v1 fatcat:zbrx735by5cnrdo3a3hdp6bjeu

A New Relaxation Approach to Normalized Hypergraph Cut [article]

Cong Xie, Wu-Jun Li, Zhihua Zhang
2015 arXiv   pre-print
Most of traditional NGC methods are based on pairwise relationships (similarities).  ...  Experimental results on a set of large hypergraph benchmarks for clustering and partitioning in VLSI domain show that RNHC can outperform the state-of-the-art methods.  ...  In social network analysis, NGC has been widely used for community detection in social networks (graphs).  ... 
arXiv:1511.02595v1 fatcat:x4umxpyz6fbzhjs7c2s56g4ixq
« Previous Showing results 1 — 15 out of 526 results