A General Deep Learning Framework for Network Reconstruction and Dynamics Learning

Abstract

Many complex processes can be viewed as dynamical systems on networks. However, in real cases, only the performances of the system are known, the network structure and the dynamical rules are not observed. Therefore, recovering latent network structure and dynamics from observed time series data are important tasks because it may help us to open the black box, and even to build up the model of a complex system automatically. Although this problem hosts a wealth of potential applications in biology, earth science, and epidemics etc., conventional methods have limitations. In this work, we introduce a new framework, Gumbel Graph Network (GGN), which is a model-free, data-driven deep learning framework to accomplish the reconstruction of both network connections and the dynamics on it. Our model consists of two jointly trained parts: a network generator that generating a discrete network with the Gumbel Softmax technique; and a dynamics learner that utilizing the generated network and one-step trajectory value to predict the states in future steps. We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.

arXiv commentv3

References in corpus (8)

• Statistical mechanics of complex networks
• The structure and function of complex networks
• Scale-free brain functional networks
• Predicting catastrophes in nonlinear dynamical systems by compressive sensing
• Revealing Network Connectivity From Dynamics
• The onset of synchronization in large networks of coupled oscillators
• Reconstructing propagation networks with natural diversity and identifying hidden sources
• Model-free inference of direct network interactions from nonlinear collective dynamics

Cited by in corpus (8)

• Deep learning of contagion dynamics on complex networks
• Symbolic Pregression: Discovering Physical Laws from Distorted Video
• Neural Information Squeezer for Causal Emergence
• Structural Inference of Networked Dynamical Systems with Universal Differential Equations
• Inferring Network Structure with Unobservable Nodes from Time Series Data
• Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic Processes
• Similarity-Based Equational Inference in Physics
• Diffusion model for relational inference