Directed Network Disassembly Method Based on Non-Backtracking Matrix

Abstract

Network disassembly refers to the removal of the minimum set of nodes to split the network into disconnected sub-part to achieve effective control of the network. However, most of the existing work only focuses on the disassembly of undirected networks, and there are few studies on directed networks, because when the edges in the network are directed, the application of the existing methods will lead to a higher cost of disassembly. Aiming at fixing the problem, an effective edge module disassembly method based on a non-backtracking matrix is proposed. This method combines the edge module spectrum partition and directed network disassembly problem to find the minimum set of key points connecting different edge modules for removal. This method is applied to large-scale artificial and real networks to verify its effectiveness. Multiple experimental results show that the proposed method has great advantages in disassembly accuracy and computational efficiency.