Large-scale complex network community detection method based on self-supervised learning type evolution

Abstract

The invention discloses a large-scale complex network community detection method based on self-supervised learning type evolution, and the method comprises the steps: determining an original population corresponding to a target network community according to the target network community; decomposing the original population into a first sub-population and a second sub-population; updating the first sub-population by adopting a method based on self-supervised learning to obtain a first updated sub-population, and updating the second sub-population by adopting a method based on breadth learning to obtain a second updated sub-population; determining an evolutionary population corresponding to the target network community according to the original population, the first updated sub-population and the second updated sub-population; and when the evolutionary population meets a termination condition, taking the evolutionary population as an optimal population. According to the method, a large-scale complex network community structure detection problem is modeled into a two-target optimization problem, the two targets are optimized at the same time through a self-supervised learning type evolution method and a method based on breadth learning, and optimal community structure detection of a large-scale complex network is achieved. 本发明公开了基于自监督学习式进化的大规模复杂网络社区检测方法，包括步骤：根据目标网络社区，确定目标网络社区对应的原始种群；将原始种群分解成第一子种群和第二子种群；采用基于自监督学习的方法对第一子种群进行更新，得到第一更新子种群，并采用基于广度学习的方法对第二子种群进行更新，得到第二更新子种群；根据原始种群、第一更新子种群以及第二更新子种群，确定目标网络社区对应的进化种群；当进化种群满足终止条件时，将进化种群作为最优种群。本发明将大规模复杂网络社区结构检测问题建模成一个两目标的优化问题，通过基于自监督学习式进化方法和基于广度学习的方法同时优化这两个目标，实现对大规模复杂网络的最优社区结构检测。