Machine learning dismantling and early-warning signals of disintegration in complex systems

TL;DR

This paper presents a machine learning approach that identifies key nodes for dismantling complex networks and predicts collapse risks, outperforming traditional heuristics and aiding systemic risk assessment.

Contribution

It introduces a machine learning method capable of analyzing large complex systems to efficiently identify critical nodes and provide early-warning signals of disintegration.

Findings

Machine learning outperforms heuristics in network dismantling.

The model predicts the probability of system disintegration.

Provides a quantitative measure of systemic risk.

Abstract

From physics to engineering, biology and social science, natural and artificial systems are characterized by interconnected topologies whose features - e.g., heterogeneous connectivity, mesoscale organization, hierarchy - affect their robustness to external perturbations, such as targeted attacks to their units. Identifying the minimal set of units to attack to disintegrate a complex network, i.e. network dismantling, is a computationally challenging (NP-hard) problem which is usually attacked with heuristics. Here, we show that a machine trained to dismantle relatively small systems is able to identify higher-order topological patterns, allowing to disintegrate large-scale social, infrastructural and technological networks more efficiently than human-based heuristics. Remarkably, the machine assesses the probability that next attacks will disintegrate the system, providing a quantitative method to quantify systemic risk and detect early-warning signals of system's collapse. This demonstrates that machine-assisted analysis can be effectively used for policy and decision making to better quantify the fragility of complex systems and their response to shocks.