Universal structural estimator and dynamics approximator for complex networks

Abstract

Revealing the structure and dynamics of complex networked systems from observed data is of fundamental importance to science, engineering, and society. Is it possible to develop a universal, completely data driven framework to decipher the network structure and different types of dynamical processes on complex networks, regardless of their details? We develop a Markov network based model, sparse dynamical Boltzmann machine (SDBM), as a universal network structural estimator and dynamics approximator. The SDBM attains its topology according to that of the original system and is capable of simulating the original dynamical process. We develop a fully automated method based on compressive sensing and machine learning to find the SDBM. We demonstrate, for a large variety of representative dynamical processes on model and real world complex networks, that the equivalent SDBM can recover the network structure of the original system and predicts its dynamical behavior with high precision.

References in corpus (13)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Statistical physics of social dynamics
• Hierarchical structure and the prediction of missing links in networks
• Revealing Network Connectivity From Dynamics
• Reconstructing propagation networks with natural diversity and identifying hidden sources
• Noise bridges dynamical correlation and topology in coupled oscillator networks
• Mean Field Theory For Non-Equilibrium Network Reconstruction
• Extreme events on complex networks
• A statistical inference approach to structural reconstruction of complex networks from binary time series
• Mean-field theory for the inverse Ising problem at low temperatures
• Self-organized Boolean game on networks
• A universal data based method for reconstructing complex networks with binary-state dynamics
• Inference of kinetic Ising model on sparse graphs

Cited by in corpus (3)

• How Entropic Regression Beats the Outliers Problem in Nonlinear System Identification
• Interpretable machine learning for high-dimensional trajectories of aging health
• Data based reconstruction of complex multiplex networks