在复杂网络中的社区发现一直受到广泛的关注,基于模块度最大化的方法是目前流行的社区发现技术.提出一种基于资源分配(RA)指标和多步贪婪凝聚策略的模块度最大化社区发现算法RALPA(Resource Allocation-based of Label propagation Algorithm).该算法利用准确衡量节点间相似性的RA指标,通过最大约束标记传播模型使社区内部节点拥有较高的相似性,与社区外部的节点拥有较低的相似性.然后,通过多步贪婪凝聚策略将划分模块度增加最大的多对小社区进行合并.实验结果表明,该算法不仅避免了对节点更新顺序的敏感和易得到平凡解的问题,而且提高了算法的稳定性和社区划分的精度.%Community detection in complex networks have received wide attention, and the method based on modularity maximization is the popular community detection technology.In this paper, a modularity maximization community detection algorithm named RALPA (Resource Allocation-based of Label Propagation Algorithm) is proposed, which is based on resource allocation (RA) and multi-step greedy cohesion strategy.The algorithm uses the RA index to measure the similarity between nodes accurately.By using the maximum constraint label propagation model, the internal nodes of the community have high similarity, and have low similarity with the nodes outside the community.Then, through the multi-step greedy cohesion strategy, the multi-pair small communities with the largest increase of partitioning degree will be merged.The experimental results show that the proposed algorithm not only avoids the problem of the sensitivity of node update order and the trivial solution, but also improves the stability of the algorithm and the accuracy of community division.
展开▼
