arXiv subjects

Maël Canu

Publications and source records attributed to Maël Canu.

3 recordsLinked to original sources

arXiv2017

Overlapping Community Detection by Local Decentralised Vertex-centred Process

This paper focuses on the identification of overlapping communities, allowing nodes to simultaneously belong to several communities, in a decentralised way. To that aim it proposes LOCNeSs, an algorithm specially designed to run in a decentralised environment and to limit propagation, two essential characteristics to be applied in mobile networks. It is based on the exploitation of the preferential attachment mechanism in networks. Experimental results show that LOCNeSs is stable and achieves good overlapping vertex identification.

cs.SI↗

arXiv2016

Vertex-centred Method to Detect Communities in Evolving Networks

Finding communities in evolving networks is a difficult task and raises issues different from the classic static detection case. We introduce an approach based on the recent vertex-centred paradigm. The proposed algorithm, named DynLOCNeSs, detects communities by scanning and evaluating each vertex neighbourhood, which can be done independently in a parallel way. It is done by means of a preference measure, using these preferences to handle community changes. We also introduce a new vertex neighbourhood preference measure, CWCN, more efficient than current existing ones in the considered context. Experimental results show the relevance of this measure and the ability of the proposed approach to detect classical community evolution patterns such as grow-shrink and merge-split.

cs.SI↗

arXiv2015

Fast community structure local uncovering by independent vertex-centred process

This paper addresses the task of community detection and proposes a local approach based on a distributed list building, where each vertex broadcasts basic information that only depends on its degree and that of its neighbours. A decentralised external process then unveils the community structure. The relevance of the proposed method is experimentally shown on both artificial and real data.

cs.SI↗