Community detection in networks: A user guide

Fortunato, Santo; Hric, Darko

doi:10.1016/j.physrep.2016.09.002

Cited by 1,739 publications

(1,441 citation statements)

References 173 publications

(261 reference statements)

Supporting

Mentioning

1,421

Contrasting

Unclassified

Order By: Relevance

“…Several methods exist for the detection of clusters of nodes (communities) in networks (Fortunato and Hric, 2016), and their application to citation networks has been extensively explored (Šubelj et al, 2016). One particularly popular method relies on modularity maximization (Newman and Girvan, 2004), for which a fast implementation exists, known as the Louvain algorithm (Blondel et al, 2008), which has also been extended to incorporate a resolution parameter, helping to tune the size and thus resulting number of clusters (Reichardt and Bornholdt, 2006).…”

Section: The Recent Historiography On Venicementioning

confidence: 99%

The Core Literature of the Historians of Venice

Colavizza

2017

Front. Digit. Humanit.

View full text Add to dashboard Cite

Over the past decades, the humanities have been accumulating a growing body of literature at an increasing pace. How does this impact their traditional organization into disciplines and fields of research therein? This article considers history, by examining a citation network among recent monographs on the history of Venice. The resulting network is almost connected, clusters of monographs are identifiable according to specific disciplinary areas (history, history of architecture, and history of arts) or periods of time (middle ages, early modern, and modern history), and a map of the recent trends in the field is sketched. Most notably a set of highly cited works emerges as the core literature of the historians of Venice. This core literature comprises a mix of primary sources, works of reference, and scholarly monographs and is important in keeping the field connected: monographs usually cite a combination of few core and a variety of less well-cited works. Core primary sources and works of reference never age, while core scholarly monographs are replaced at a very slow rate by new ones. The reliance of new publications on the core literature is slowly rising over time, as the field gets increasingly more varied.

show abstract

Section: The Recent Historiography On Venicementioning

confidence: 99%

The Core Literature of the Historians of Venice

Colavizza

2017

Front. Digit. Humanit.

View full text Add to dashboard Cite

show abstract

“…The LFR benchmark is widely used for benchmarking community detection algorithms, as it can be used to generate a wide variety of graphs with ground truth communities [2,4,8]. We briefly describe the LFR benchmark here, for details we refer the reader to the original publications [11,12].…”

Section: Synthetic Graphsmentioning

confidence: 99%

“…In order to formalize the fuzzy concept of a community, many quality measures for determining what a good community is and even more algorithms for detecting communities have been proposed. We refer the interested reader to [1][2][3] for an overview.…”

Section: Introductionmentioning

confidence: 99%

Local Community Detection Based on Small Cliques

2017

View full text Add to dashboard Cite

Community detection aims to find dense subgraphs in a network. We consider the problem of finding a community locally around a seed node both in unweighted and weighted networks. This is a faster alternative to algorithms that detect communities that cover the whole network when actually only a single community is required. Further, many overlapping community detection algorithms use local community detection algorithms as basic building block. We provide a broad comparison of different existing strategies of expanding a seed node greedily into a community. For this, we conduct an extensive experimental evaluation both on synthetic benchmark graphs as well as real world networks. We show that results both on synthetic as well as real-world networks can be significantly improved by starting from the largest clique in the neighborhood of the seed node. Further, our experiments indicate that algorithms using scores based on triangles outperform other algorithms in most cases. We provide theoretical descriptions as well as open source implementations of all algorithms used.

show abstract

“…The discovery of clustering structure in graphs is important as they often correspond to common/latent properties (e.g., interest, role and affiliation) [5]. Although sampling provides a potential solution for inferring and approximating global, latent properties in original graphs, most sampling techniques are not particularly designed to retain the essential property: the inherent clustering structure [12].…”

Section: Clustering Structure In Graphsmentioning

confidence: 99%

“…Higher value of δ -precision means that the obtained clusters of G s are more precisely representative of the ground-truth clusters of G while higher value of δ -recall indicates the ground-truth clusters of G are more successfully covered by the obtained clusters of G s . Secondly, we also employ several representative metrics widely used for evaluating clusters in the graph including: adjusted Rand index (ARI) [5], normalized mutual information (NMI) [5] and accuracy for number of clusters (ANC) [11] to evaluate the clustering results of the sampled graphs. Note that those metrics are designed solely to assess the clustering quality on the entire graph, not particularly on the sample.…”

Section: Measurementsmentioning

confidence: 99%

Clustering-Structure Representative Sampling from Graph Streams

Zhang

Zhu

Pei

et al. 2017

Complex Networks &Amp; Their Applications VI

View full text Add to dashboard Cite

Most existing sampling algorithms on graphs (i.e., network-structured data) focus on sampling from memory-resident static graphs and assume the entire graphs are always available. However, the graphs encountered in modern applications are often too large and/or too dynamic to be processed with limited memory. Furthermore, existing sampling techniques are inadequate for preserving the inherent clustering structure, which is an essential property of complex networks.To tackle these problems, we propose a new sampling algorithm that dynamically maintains a representative sample and is capable of retaining clustering structure in graph streams at any time. Performance of the proposed algorithm is evaluated through empirical experiments using real-world networks. The experimental results have shown that our proposed CPIES algorithm can produce clustering-structure representative samples and outperforms current online sampling algorithms.

show abstract

Community detection in networks: A user guide

Cited by 1,739 publications

References 173 publications

The Core Literature of the Historians of Venice

The Core Literature of the Historians of Venice

Local Community Detection Based on Small Cliques

Clustering-Structure Representative Sampling from Graph Streams

Contact Info

Product

Resources

About