Detecting structural perturbations from time series with deep learning
This work addresses the challenge of preventing catastrophes in complex systems by detecting structural perturbations, offering a practical tool for studying resilience in real-world applications, though it is incremental as it applies existing deep learning methods to this specific problem.
The authors tackled the problem of inferring structural causes of disturbances in networked systems from functional time series, showing that their graph neural network approach outperforms typical reconstruction methods and matches Bayesian inference accuracy across various systems like epidemics and neural dynamics.
Small disturbances can trigger functional breakdowns in complex systems. A challenging task is to infer the structural cause of a disturbance in a networked system, soon enough to prevent a catastrophe. We present a graph neural network approach, borrowed from the deep learning paradigm, to infer structural perturbations from functional time series. We show our data-driven approach outperforms typical reconstruction methods while meeting the accuracy of Bayesian inference. We validate the versatility and performance of our approach with epidemic spreading, population dynamics, and neural dynamics, on various network structures: random networks, scale-free networks, 25 real food-web systems, and the C. Elegans connectome. Moreover, we report that our approach is robust to data corruption. This work uncovers a practical avenue to study the resilience of real-world complex systems.