论文部分内容阅读
为提高大型网络的社区发现精度和效果,解决叶节点存在的局部极值化问题,提出基于局部模块性增量超点Louvain剪枝技术的动态社区发现方法.首先,对网络社区进行模型定义,并给出社区发现的模块度函数,同时针对传统模块度函数存在的叶节点处置问题,对模块度函数进行改进;其次,在进行模块度函数改进基础上,针对叶节点问题利用超节点构建Louvain剪枝技术;最后,通过在社区发现算例上实验对比显示,所提算法相对于对比算法的模块度指标提升7.2％以上,验证了所提算法有效性.“,”In order to improve the discovery accuracy and effect of large network communities,and solve the local extremum problem of leaf nodes,a detection method based on the local module of increment of super node Louvain pruning technique of dynamic community is proposed here.Firstly,the model is defined,and the module function of the community is given.At the same time,the function of the module is improved,and the function of the leaf node is used to deal with the problem;Secondly,based on the improved function module,according to the leaf node,we use the super node pruning technique to construct Louvain;Finally,through the comparison of the experimental results in the community,the proposed algorithm is improved by more than 7.2％ compared with the modular degree of the contrast algorithm,which verifies the effectiveness of the proposed algorithm.