MCMC Louvain for Online Community Detection

Community detection has become very popular in network analysis the last decades. Its range of applications include social sciences, biology and complex systems, such as the worldwide-web, protein-protein interactions, or social networks (see [5] for a thorough exposition of the topic). To tackle this problem, spectral approaches have been introduced in [12] or [18], inspired from the so-called spectral clustering problem (see [10]). However, the treatment of larger and larger graphs has been investigated and modularity-based algorithms has been proposed. This class of algorithms maximize a quality index called modularity, introduced in [13].