Fast colonization algorithm for seed selection in complex networks based on community detection

An ongoing challenge in network science is influence maximization (IM), which sets out to define those nodes which maximize the dissemination of influence. Most of the recent research proposals on the IM problem offer solutions that are still highly time consuming for usage in the context of real-world complex networks. This article develops a novel seed selection framework based on the principle of maximizing influence at the community level with an emphasis on global homogeneous seed spacing. Our proposed framework, called Colonise, consists of the following stages: (i) community tuning, (ii) node centrality computation, and (iii) seed assignment. Particularly, phase (i) iteratively breaks down the network into communities, using the Louvain method, based on the number of desired seeds; phase (ii) measures a target node centrality on each community to reduce the number of seed candidates; phase (iii) assigns nodes as seeds from the highest centrality nodes found in each community. In contrast to global centrality-based seed selection, we exploit the structure of communities and circumvent overlapped assignment, such that we select efficiently the number of seed nodes to boost information diffusion. The simulation results-based on 12 diverse synthetic and real-world networks, and employing the SIR epidemic model-prove that our proposed Colonise algorithm surpasses state-of-the-art selection methods in all simulated scenarios, with an increased diffusion efficiency ranging between +0.15% up to +173.53% (22.36% on average), without compromising either diffusion coverage or speed.