An Approach to Assess Swarm Intelligence Algorithms Based on Complex Networks

The growing number of novel swarm-based meta-heuristics has been raising debates regarding their novelty. These algorithms often claim to be inspired by different concepts from nature but the proponents of these seldom demonstrate whether the novelty goes beyond the nature inspiration. In this work, we employed the concept of interaction networks to capture the interaction patterns that take place in algorithms during the optimisation process. The analyses of these networks reveal aspects of the algorithm such as the tendency to achieve premature convergence, population diversity, and stability. Furthermore, we make use of portrait divergence, a newly-proposed state-of-the-art metric, to assess structural similarities between our interaction networks. Using this approach to analyse the cat swarm optimization (CSO) algorithm, we were able to identify some of the algorithm's characteristics, assess the impact of one of the CSO's parameters, and compare this algorithm to two other well-known methods (particle swarm optimization and artificial bee colony). Lastly, we discuss the relationship between the interaction network and the performance of the algorithms assessed.