基于保守合并策略的复杂网络社区结构发现

Complex Networks Community Detection with Conservative Cluster Merging

为了有效的进行复杂网络社区结构发现,在CNM算法的基础上引进了一种具有额外头部节点的堆数据结构,在社区合并的过程中采用有偏的随机抽样方法,实现了较为保守的合并策略。随机合并算法的输出有更多的机会到达模块度函数的平台区域,在通常情况下其平均表现超过了原始CNM算法。在合成和真实的网络上验证了所提算法的可行性和有效性。

Based on the CNM algorithm, we propose a revised heap structure with an extra head array which allows more flexible merging during the agglomerating procedure. Thus we actually implement a conservative merging strategy for community detection. The proposed method tends to achieve the plateau area of the sub-optimal solutions of the modularity function and outperform the original CNM algorithm under typical situation. Experiments on synthesized and real world networks verify the feasibility and validity of the proposed method.