Reinforcement Learning-Based Network Dismantling by Targeting Maximum-Degree Nodes in the Giant Connected Component
Shixuan Liu,
Tianle Pu,
Li Zeng,
Yunfei Wang,
Haoxiang Cheng,
Zhong Liu
Affiliations
Shixuan Liu
Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
Tianle Pu
Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
Li Zeng
Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
Yunfei Wang
National Key Laboratory of Information Systems Engineering, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
Haoxiang Cheng
Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
Zhong Liu
Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
Tackling the intricacies of network dismantling in complex systems poses significant challenges. This task has relevance across various practical domains, yet traditional approaches focus primarily on singular metrics, such as the number of nodes in the Giant Connected Component (GCC) or the average pairwise connectivity. In contrast, we propose a unique metric that concurrently targets nodes with the highest degree and reduces the GCC size. Given the NP-hard nature of optimizing this metric, we introduce MaxShot, an innovative end-to-end solution that leverages graph representation learning and reinforcement learning. Through comprehensive evaluations on both synthetic and real-world datasets, our method consistently outperforms leading benchmarks in accuracy and efficiency. These results highlight MaxShot’s potential as a superior approach to effectively addressing the network dismantling problem.
