A Universal Framework for Reconstructing Complex Networks and Node Dynamics from Discrete or Continuous Dynamics Data

TL;DR

This paper introduces a universal neural network-based framework that simultaneously reconstructs complex network structures and node dynamics from diverse time-series data, demonstrating high accuracy and robustness.

Contribution

It presents a novel differentiable Bernoulli sampling approach combined with neural networks for joint network and dynamics reconstruction from various data types.

Findings

Successfully reconstructs different network structures and node dynamics.

Performs well on binary, discrete, and continuous data.

Robust against noise and missing data.

Abstract

Many dynamical processes of complex systems can be understood as the dynamics of a group of nodes interacting on a given network structure. However, finding such interaction structure and node dynamics from time series of node behaviours is tough. Conventional methods focus on either network structure inference task or dynamics reconstruction problem, very few of them can work well on both. This paper proposes a universal framework for reconstructing network structure and node dynamics at the same time from observed time-series data of nodes. We use a differentiable Bernoulli sampling process to generate a candidate network structure, and use neural networks to simulate the node dynamics based on the candidate network. We then adjust all the parameters with a stochastic gradient descent algorithm to maximize the likelihood function defined on the data. The experiments show that our model can recover various network structures and node dynamics at the same time with high accuracy. It can also work well on binary, discrete and continuous time-series data, and the reconstruction results are robust against noise and missing information.