• Corpus ID: 219558941

Detecting structural perturbations from time series with deep learning

  title={Detecting structural perturbations from time series with deep learning},
  author={Edward Laurence and Charles Murphy and Guillaume St‐Onge and Xavier Roy-Pomerleau and Vincent Thibeault},
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… 

Figures and Tables from this paper

Deep learning of stochastic contagion dynamics on complex networks

This work proposes a complementary approach based on deep learning where the effective local mechanisms governing a dynamic are learned automatically from time series data and demonstrates how deep learning offers a new and complementary perspective to build effective models of contagion dynamics on networks.

Duality between predictability and reconstructability in complex systems

It is shown that predictability and reconstructability, even though closely connected by the mutual information, can behave differently, even in a dual manner, and it is proved how such duality universally emerges when changing the number of steps in the process.

Deep learning of contagion dynamics on complex networks

This work proposes a complementary approach based on deep learning where effective local mechanisms governing a dynamic on a network are learned from time series data and demonstrates how deep learning offers a new and complementary perspective to build effective models of contagion dynamics on networks.



Extracting neuronal functional network dynamics via adaptive Granger causality analysis

A dynamic estimation and inference paradigm for extracting functional neuronal network dynamics in the sense of Granger by integrating techniques from adaptive filtering, compressed sensing, point process theory, and high-dimensional statistics is developed.

Network Reconstruction and Community Detection from Dynamics

It is shown that the joint reconstruction with community detection has a synergistic effect, where the edge correlations used to inform the existence of communities are also inherently used to improve the accuracy of the reconstruction which, in turn, can better inform the uncovering of communities.

Spectral Dimension Reduction of Complex Dynamical Networks

This work introduces a method that reduces any network to a simplified low-dimensional version, which can then be used to describe the collective dynamics of the original system and offers a novel framework to relate the structure of networks to their dynamics and to study the resilience of complex systems.

Inferring network topology from complex dynamics

This work presents an analytical solution to the inverse problem of finding the network topology from observing a time series of state variables only, and provides a conceptually new step towards reconstructing a variety of real-world networks, including gene and protein interaction networks and neuronal circuits.

Predicting tipping points in mutualistic networks through dimension reduction

The reduced model can serve as a paradigm for understanding and predicting the tipping point dynamics in real world mutualistic networks for safeguarding pollinators and the general principle can be extended to a broad range of disciplines to address the issues of resilience and sustainability.

Predicting missing links and identifying spurious links via likelihood analysis

An algorithmic framework where a network’s probability is calculated according to a predefined structural Hamiltonian that takes into account the network organizing principles, and a non-observed link is scored by the conditional probability of adding the link to the observed network is used.

Network deconvolution as a general method to distinguish direct dependencies in networks

This work presents a general method for inferring direct effects from an observed correlation matrix containing both direct and indirect effects, and introduces an algorithm that removes the combined effect of all indirect paths of arbitrary length in a closed-form solution by exploiting eigen-decomposition and infinite-series sums.

Epidemic processes in complex networks

A coherent and comprehensive review of the vast research activity concerning epidemic processes is presented, detailing the successful theoretical approaches as well as making their limits and assumptions clear.

Network link prediction by global silencing of indirect correlations

The fundamental properties of dynamical correlations in networks are exploited to develop a method to silence indirect effects and help translate the abundant correlation data into valuable local information, with applications ranging from link prediction to inferring the dynamical mechanisms governing biological networks.

Wisdom of crowds for robust gene network inference

A comprehensive blind assessment of over 30 network inference methods on Escherichia coli, Staphylococcus aureus, Saccharomyces cerevisiae and in silico microarray data defines the performance, data requirements and inherent biases of different inference approaches, and provides guidelines for algorithm application and development.