Deep-learning-aided dismantling of interdependent networks

2026-09-23

AI Summary

This study addresses the challenge of optimally dismantling multilayer interdependent networks, where cross-layer coupling effects render traditional single-layer node removal strategies ineffective. To overcome this limitation, this work proposes MultiDismantler, an algorithm that pioneers the application of deep reinforcement learning to this task. By modeling multiplex networks to achieve a unified representation of cross-layer topology, the approach is trained on small-scale synthetic graphs to enable generalization to large-scale real-world networks. Breaking through the constraints of single-layer perspectives, the proposed method significantly outperforms existing baselines in critical scenarios such as epidemic containment and mitigating cascading failures in essential infrastructure. Ultimately, this research provides an efficient new paradigm for robustness analysis in complex networks.

Abstract

Identifying the minimal set of nodes whose removal breaks a complex network apart, also referred as the network dismantling problem, is a highly non-trivial task with applications in multiple domains. Whereas network dismantling has been extensively studied over the past decade, research has primarily focused on the formulations of the optimization problem for single-layer networks, neglecting that many, if not all, real networks display multiple layers of interdependent interactions. In such networks, the optimization problem is fundamentally different as the effect of removing nodes propagates within and across layers in a way that can not be predicted using a single-layer perspective. Here, we propose a dismantling algorithm named MultiDismantler, which leverages multiplex network representation and deep reinforcement learning to optimally dismantle multi-layer interdependent networks. MultiDismantler is trained on small synthetic multiplex graphs; when applied to large, real and synthetic networks, it displays exceptional dismantling performance, clearly outperforming all existing methods that rely on a single-layer approach to network dismantling. We show that MultiDismantler is effective in guiding strategies for the containment of diseases in social networks characterized by multiple layers of social interactions. Also, we show that MultiDismantler is useful in the design of protocols aimed at delaying the onset of cascading failures in interdependent critical infrastructures.

Problem

• network dismantling
• interdependent networks
• multiplex networks
• node removal
• cascading failures

Innovation

• Deep Reinforcement Learning
• Network Dismantling
• Multiplex Networks
• Interdependent Networks
• MultiDismantler