基于网络预处理的改进标签传播算法

Improved Label Propagation Algorithm Based on Network Preprocessing

LPA中存在的随机策略,严重破坏算法的鲁棒性.随着大数据时代的来临,复杂网络的规模不断增大,从而造成算法的运算量增加,收敛速度减慢.针对这一问题,提出了一种新的改进标签传播算法-KLPA.首先,对初始网络预处理:利用K-Shell指数将网络划分成核心-边缘层次,去除边缘层节点,赋予核心层的节点标签.其次,改进标签传播策略对预处理网络进行社区划分.最后,实验证明KLPA算法减小网络规模,提高了社区划分质量,同时也加快了算法的收敛速度.

The stochastic strategy exists in LPA, which seriously destroys the robustness of the algorithm. With the advent of big data age, the scale of complex networks is increasing, which causes the computation of the algorithm to increase and the convergence rate to slow down. A new improved label propagation algorithm-KLPA is proposed to solve this problem. Firstly, the network is preprocessed by using the K-Shell index to divide the network into a core-edge layer, remove the nodes of the edge layer, and assign labels to the nodes in the core layer. Secondly, the improved propagation strategy is used to divide the community for preprocessing network. Finally, experiments show that the KLPA algorithm reduces the size of the network, effectively improves the quality of community division, and accelerates the convergence rate of the algorithm.