Abstract

Surprising insights in community structures of complex networks have raised tremendous interest in developing various kinds of community detection algorithms. Considering the growing size of existing networks, local community detection methods have gained attention in contrast to global methods that impose a top-down view of global network information. Current local community detection algorithms are mainly aimed to discover local communities around a given node. Besides, their performance is influenced by the quality of the source node. In this paper, we propose a community detection algorithm that outputs all the communities of a network benefiting from a set of local principles and a self-defining source node selection. Each node in our algorithm progressively adjusts its community label based on an even more restrictive level of locality, considering its neighbours local information solely. Our algorithm offers a computational complexity of linear order with respect to the network size. Experiments on both artificial and real networks show that our algorithm gains more over networks with weak community structures compared to networks with strong community structures. Additionally, we provide experiments to demonstrate the ability of the self-defining source node of our algorithm by implementing various source node selection methods from the literature.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call