Correlation and dimension relevance in multidimensional networks: a systematic taxonomy

Domgue, Félicité Gamgne; Tsopzé, Norbert; Ndoundam, René

doi:10.1007/s13278-021-00801-8

Cited by 3 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, requiring the existence of a community on all dimensions can lead to a substantial loss of information about the actual organization of the modeled system. In the last few years, we have been witnessing an increasing interest towards the importance of a dimension in multicolored community detection problem [7,28,16]. Surprisingly, the problem has been mainly investigated on methods extracting disjointed community (unlike overlapping communities), which consider the membership of a node to one community exclusively.…”

Section: Motivationsmentioning

confidence: 99%

“…A recent structured survey by Gamgne et al [16] presents a global classification of community detection methods in multicolored networks. They highlight the performance improvement of some hierarchical algorithm based on the optimization of an objective function [8,1,9,11].…”

Section: Related Workmentioning

confidence: 99%

“…These subgroups help transforming Louvain's method [6] applying a local search heuristic for potential overlapping community structures. Dealing with inter-slice correlation, as presented in [16], has revealed the need for a community detection approach based on dimensional relevance. Moreover, it favors the extraction of overlapping multi-communities.…”

Section: Motivationsmentioning

confidence: 99%

“…We used six real-world multicolored network datasets : Florentine , AUCS , Biogrid , DBLP , Bankwiring and Monastery, all of them described in [16].…”

Section: Datamentioning

confidence: 99%

See 3 more Smart Citations

UCAD: commUnity disCovery method in Attribute-based multicoloreD networks

Domgue,

Tsopze,

Ndoundam

2024

Preprint

Self Cite

View full text Add to dashboard Cite

Many hierarchical methods for community detection in multicolored networks are capable of finding clusters when there are interslice correlation between layers. However, in general, they aggregate all the links in different layer treating them as being equivalent. Therefore, such aggregation might ignore the information about the relevance of a dimension in which the node is involved. In this paper we fill this gap by proposing a hierarchical classification based-Louvain method for interslice-multicolored networks. In particular we define a new node centrality measure named \textit{Attractivity} to describe the inter-slice correlation that incorporates within and across-dimension topological features in order to identify the relevant dimension. Then, after merging dimensions through a frequential aggregation, we group nodes by their relational and attribute similarity, where attributes correspond to their relevant dimensions. We conduct an extensive experimentation using seven real-world multicolored networks, which also includes comparison with state-of-the-art methods. Results show the significance of our proposed method in discovering relevant communities over multiple dimensions and highlight its ability in producing optimal covers with higher values of the multidimensional version of the modularity function.

show abstract

Section: Motivationsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Motivationsmentioning

confidence: 99%

“…We used six real-world multicolored network datasets : Florentine , AUCS , Biogrid , DBLP , Bankwiring and Monastery, all of them described in [16].…”

Section: Datamentioning

confidence: 99%

See 2 more Smart Citations