Fluid Communities: A Competitive, Scalable and Diverse Community Detection Algorithm

We introduce a community detection algorithm (Fluid Communities) based on the idea of fluids interacting in an environment, expanding and contracting as a result of that interaction. Fluid Communities is based on the propagation methodology, which represents the state-of-the-art in terms of computational cost and scalability. While being highly efficient, Fluid Communities is able to find communities in synthetic graphs with an accuracy close to the current best alternatives. Additionally, Fluid Communities is the first propagation-based algorithm capable of identifying a variable number of communities in network. To illustrate the relevance of the algorithm, we evaluate the diversity of the communities found by Fluid Communities, and find them to be significantly different from the ones found by alternative methods. Ferran Parés∗ Barcelona Supercomputing Center (BSC), Barcelona, Spain, e-mail: [email protected] Dario Garcia-Gasulla∗ Barcelona Supercomputing Center (BSC), Barcelona, Spain, e-mail: [email protected] Armand Vilalta Barcelona Supercomputing Center (BSC), Barcelona, Spain Jonatan Moreno Barcelona Supercomputing Center (BSC), Barcelona, Spain Eduard Ayguadé Barcelona Supercomputing Center (BSC) & UPC BarcelonaTECH, Barcelona, Spain Jesús Labarta Barcelona Supercomputing Center (BSC) & UPC BarcelonaTECH, Barcelona, Spain Ulises Cortés Barcelona Supercomputing Center (BSC) & UPC BarcelonaTECH, Barcelona, Spain Toyotaro Suzumura Barcelona Supercomputing Center (BSC) & IBM T.J. Watson, New York, USA ∗ Both authors contributed equally to this work 1 ar X iv :1 70 3. 09 30 7v 3 [ cs .D S] 9 O ct 2 01 7 2 Parés F., Garcia-Gasulla D. et al.