Recursive filtration method for detecting community structure in networks

Shen, Yi; Pei, Wei; Wang, Kai; Li, Tao; Wang, Shaoping

doi:10.1016/j.physa.2008.08.029

Cited by 11 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sales-Pardo et al [42] proposed a method uncovering the hierarchical organizations of nodes based on a new nodeaffinity metric and on searching for the local maxima of modularity. Shen et al [43] designed a multi-step algorithm named EAGLE to detect hierarchical and overlapping community structures, where maximal cliques in the graph are used as the seed set and an agglomerative process relying on modularity maximization helps establish the hierarchy. A similar multi-step algorithm named SHRINK was proposed by Sun et al [34], where each node is assigned with an initial label and the (multi-ary, as opposed to binary) hierarchical community structure is gradually established by measuring the modularity gain of merging end-communities.…”

Section: A5 Multi-step Detection and Hierarchical Structuresmentioning

confidence: 99%

See 1 more Smart Citation

Self-falsifiable hierarchical detection of overlapping communities on social networks

Zhang

2020

New J. Phys.

View full text Add to dashboard Cite

No community detection algorithm can be optimal for all possible networks, thus it is important to identify whether the algorithm is suitable for a given network. We propose a multi-step algorithmic solution scheme for overlapping community detection based on an advanced label propagation process, which imitates the community formation process on social networks. Our algorithm is parameter-free and is able to reveal the hierarchical order of communities in the graph. The unique property of our solution scheme is self-falsifiability; an automatic quality check of the results is conducted after the detection, and the fitness of the algorithm for the specific network is reported. Extensive experiments show that our algorithm is self-consistent, reliable on networks of a wide range of size and different sorts, and is more robust than existing algorithms on both sparse and large-scale social networks. Results further suggest that our solution scheme may uncover features of networks' intrinsic community structures.Community detection is a central topic in network science. Pioneered by works represented by Palla et al [1], in recent years more and more studies focus on the detection of overlapping communities as opposed to exhaustive communities, a division also regarded as soft-partitioning versus hard-partitioning. Besides relying on the optimization of certain metrics, e.g. modularity [2], conductance [3], fitness [4], or aggregative metric based on link prediction algorithms [5] etc, as the extensively-studied traditional approach for detecting exhaustive communities, for overlapping communities, a lot of new tools are designed based on various ideas, including link communities [6, 7], clique percolation [8], seed set expansion [3,[9][10][11][12], label propagation [13][14][15][16], local spectral clustering method [17], and methods based on statistical inference, such as Infomap [18], the stochastic block model (SBM,[19,20]; in particular, methods adopting the belief propagation algorithm [21,22]), and other generative models [23,24].Despite the success of different solution schemes on various application fronts, some weak points of existing community detection algorithms could be pinned down in practice, which we believe might be problematic in certain cases (see appendix A for a detailed discussion). These weaknesses include: (1) many solution schemes are over-parameterized, and in some cases the tuning of parameters depends largely on unwarranted heuristics;(2) many scalable methods based on the seed set expansion process [2-4, 9, 25-28] may lack well-designed seeding strategies [10,11,29] and often rely on ad-hoc strategies; (3) some algorithms that claim to be local, as opposed to methods based on an optimization over the entire graph, in fact still optimize on the community level and thus do not guarantee complete locality; (4) the number of communities in the graph is often predetermined in certain algorithms, which might not be a good treatment, despite its claimed advantage [30] and the possible determina...

show abstract

Section: A5 Multi-step Detection and Hierarchical Structuresmentioning

confidence: 99%

“…(v) Order of communities. Communities on graphs should follow a hierarchical order [4,26,[40][41][42][43]: iteratively, the aggregation of small communities gives rise to bigger communities, and the entire graph is the single ultimate community.…”

mentioning

confidence: 99%

Self-falsifiable hierarchical detection of overlapping communities on social networks

Zhang

2020

New J. Phys.

View full text Add to dashboard Cite

show abstract

“…Pons et al [50] proposed the Walktrap algorithm by using the intuitive report that the random walks will be made trap in zones dense, in other words when a walker is in a community it has a strong probability of remaining in the same community at the following stage. The authors define metric of distance which is related to the spectral approaches which are based on the fact that two close nodes belonging to the same community have similar components on the principal eigenvectors.…”

Section: Random Walk Techniquesmentioning

confidence: 99%

“…Shen et al [50] have proposed a filtration recursive method using a random model for networks in order to simultaneously carry out the suppression of several edges in each operation of filtration.…”

Section: Algorithm Based On Local Proprietiesmentioning

confidence: 99%

Taxonomy and Survey Of Community Discovery Methods in Complex Networks

Drif¹,

Boukerram²

2014

IJCSES

View full text Add to dashboard Cite

show abstract

“…Modularity, which is detailed in [19], is a score for measuring the density of links inside and outside communities that helps in determining the belonging of a node to a certain community. Other works that we can find adopt divisive algorithms that work on splitting a network by deleting edges [22]. Additionally, others use agglomerative algorithms that work on adding nodes to groups until no individual node remains [11].…”

Section: Related Workmentioning

confidence: 99%

Highlighting Stakeholder Communities to Support Requirements Decision-Making

Azmeh

Mirbel

Crescenzo

2013

Requirements Engineering: Foundation for Software Quality

View full text Add to dashboard Cite

Abstract. [Context & motivation] Stakeholders participation is recognized as a key issue in the development of useful and usable systems. The Web has given rise to a growing number of collaborative working tools that facilitated the participation of stakeholders (and especially end-users). These tools create new opportunities of practice regarding requirement elicitation. [Question/problem] Nevertheless, they result in an information overload lacking structure and semantics. Consequently, requirements analysis and selection becomes more challenging.[Principal ideas/results] In this paper, we propose an approach based on semantic web languages as well as concept lattices to identify relevant groups of stakeholders depending on their past participation.[Contribution] These groups can be used to enable facilitated decision-making and handling of requirements. We detail the different steps and the possible configurations, using an example inspired by a collaborative software development environment.

show abstract

Recursive filtration method for detecting community structure in networks

Cited by 11 publications

References 34 publications

Self-falsifiable hierarchical detection of overlapping communities on social networks

Self-falsifiable hierarchical detection of overlapping communities on social networks

Taxonomy and Survey Of Community Discovery Methods in Complex Networks

Highlighting Stakeholder Communities to Support Requirements Decision-Making

Contact Info

Product

Resources

About