Deep-learning-aided dismantling of interdependent 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.
Versions
Related
- Probabilistic Deep Learning Framework for Phase Transformation Forecasting aided by In Situ High temperature Microscopy
- Percolation on interdependent one-dimensional long-range networks
- DNNsolver: Accurate and Efficient Deep Learning Modeling of Polarization-Sensitive Diffractive Neural Networks
- Machine Learning Aided Computational Discovery of Boride Substrates for Borophene Synthesis
- Transfer learning-aided, artificial intelligence approach to evaluate optical properties of materials for classical and quantum photonic applications
BibTeX
@misc{gu2026deeplearningaided,
title = {{Deep-learning-aided dismantling of interdependent networks}},
author = {Weiwei Gu and Chen Yang and Lei Li and Jinqiang Hou and Filippo Radicchi},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28977},
eprint = {2609.28977},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28977},
}
RIS
TY - UNPB
TI - Deep-learning-aided dismantling of interdependent networks
AU - Weiwei Gu
AU - Chen Yang
AU - Lei Li
AU - Jinqiang Hou
AU - Filippo Radicchi
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.28977
UR - https://arxiv.org/abs/2609.28977
AB - 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.
ER -