arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.06432cs.SIcs.DCcs.DS
收藏

线性时间分层社区发现

Linear-time Hierarchical Community Detection

Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh, Sungchul Kim

摘要:

图中的社区发现具有许多重要和基本的应用,包括在分布式系统、压缩、图像分割、分而治之的图算法(诸如嵌套解剖、文档和词聚类、电路设计等)中。寻找这些密集连接的区域的图仍然是一个重要的和具有挑战性的问题。大多数工作都集中在扩展现有的方法来处理大型图。这些方法通常将图划分为两个或更多个社区。在这项工作中,我们专注于分层社区发现问题(即,找到从最低粒度到最大粒度的密集社区结构的层级),并描述了一种方法,该方法相对于边的数量在线性时间内运行,因此对于大规模网络是快速和有效的。实验定量地证明了该方法的有效性。最后,我们展示了一个应用程序,它可视化大型网络与数十万个节点/链接。

英文摘要:

Community detection in graphs has many important and fundamental applications including in distributed systems, compression, image segmentation, divide-and-conquer graph algorithms such as nested dissection, document and word clustering, circuit design, among many others. Finding these densely connected regions of graphs remains an important and challenging problem. Most work has focused on scaling up existing methods to handle large graphs. These methods often partition the graph into two or more communities. In this work, we focus on the problem of hierarchical community detection (i.e., finding a hierarchy of dense community structures going from the lowest granularity to the largest) and describe an approach that runs in linear time with respect to the number of edges and thus fast and efficient for large-scale networks. The experiments demonstrate the effectiveness of the approach quantitatively. Finally, we show an application of it for visualizing large networks with hundreds of thousands of nodes/links.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑