Structural Inference of Networked Dynamical Systems with Universal Differential Equations

Abstract

Networked dynamical systems are common throughout science in engineering; e.g., biological networks, reaction networks, power systems, and the like. For many such systems, nonlinearity drives populations of identical (or near-identical) units to exhibit a wide range of nontrivial behaviors, such as the emergence of coherent structures (e.g., waves and patterns) or otherwise notable dynamics (e.g., synchrony and chaos). In this work, we seek to infer (i) the intrinsic physics of a base unit of a population, (ii) the underlying graphical structure shared between units, and (iii) the coupling physics of a given networked dynamical system given observations of nodal states. These tasks are formulated around the notion of the Universal Differential Equation, whereby unknown dynamical systems can be approximated with neural networks, mathematical terms known a priori (albeit with unknown parameterizations), or combinations of the two. We demonstrate the value of these inference tasks by investigating not only future state predictions but also the inference of system behavior on varied network topologies. The effectiveness and utility of these methods is shown with their application to canonical networked nonlinear coupled oscillators.

References in corpus (19)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Neural Message Passing for Quantum Chemistry
• Synchronization in complex networks
• Categorical Reparameterization with Gumbel-Softmax
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Neural Ordinary Differential Equations
• Topology of biological networks and reliability of information processing
• Robust Reconstruction of Complex Networks from Sparse Data
• Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network
• Finding missing edges in networks based on their community structure
• Graph Neural Ordinary Differential Equations
• A General Deep Learning Framework for Network Reconstruction and Dynamics Learning
• Emergence of Symmetry in Complex Networks
• Continuous Graph Neural Networks
• Mode-Locked Rotating Detonation Waves: Experiments and a Model Equation
• Neural Ordinary Differential Equation Control of Dynamics on Graphs
• PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
• Graph-Coupled Oscillator Networks
• Machine learning approaches for Kuramoto coupled oscillator systems

Cited by in corpus (2)

• Observing network dynamics through sentinel nodes
• Data-informed modeling of the formation, persistence, and evolution of social norms and conventions