Evolutionary Game Network Reconstruction by Memetic Algorithm with l_(1/2) Regularization

摘要

Evolutionary Game (EG) theory is effective approach to understand and analyze the widespread cooperative behaviors among individuals. Reconstructing EG networks is fundamental to understand and control its collective dynamics. Most existing approaches extend this problem to the l_1-regularization optimization problem, leading to suboptimal solutions. In this paper, a memetic algorithm (MA) is proposed to address this network reconstruction problem with l_(1/2) regularization. The problem-specific initialization operator and local search operator are integrated into MA to accelerate the convergence. We apply the method to evolutionary games taking place in synthetic and real networks, finding that our approach has competitive performance to eight state-of-the-art methods in terms of effectiveness and efficiency.