LICOD: A Leader-driven algorithm for community detection in complex networks

Abstract

Leader-driven community detection algorithms (LdCD hereafter) constitute a new trend in devising algorithms for community detection in large-scale complex networks. The basic idea is to identify some particular nodes in the target network, called leader nodes, around which local communities can be computed. Being based on local computations, they are particularly attractive to handle large-scale networks. In this paper, we describe a framework for implementing LdCD algorithms, called LICOD. We propose also a new way for evaluating performances of community detection algorithms. This consists on transforming data clustering problems into a community detection problems. External criteria for evaluating obtained clusters can then be used for comparing performances of different community detection approaches. Results we obtain show that our approach outperforms top state of the art algorithms for community detection in complex networks.

A novel cosine distance for detecting communities in complex networks

“…Our optimal modularity is greater than Q max = 0.51 by GN algorithm and Q max = 0.42 by the algorithm proposed in Ref. [32]. As shown in Fig.…”

A multi-granularity decomposition mechanism of complex tasks based on density peaks

“…Figure 5 shows MrGDM results. Table 7 briefly introduces the description of four stateof-the-art algorithms (such as ENBC [28] , Local-T [29] , CDERS [30] , and LICOD [31] ) for detecting community and describes the core concepts of each method.…”

A novel social network mining approach for customer segmentation and viral marketing

“…24 A series of algorithms tackled the problem of community detection were proposed, for a detailed survey see Refs 15,25. Owing to the increasing scale in social networks and its sparse nature; which makes the access of overall information of the network very hard; some recent algorithms designed different local based detecting methods which focus on mining local information of nodes. 26 Local based algorithms access some local network information structure properties around nodes to determine local community to which the node belongs, 26 such as the LICOD algorithm, 27 Top leaders based allocation algorithm 28 and the Hierarchical Diffusion algorithm (HDA). 29 In LICOD, 27 the algorithm uses different node ranking metrics to estimate the node's role.…”