cs.LGNov 14, 2024

Neural Graph Simulator for Complex Systems

Authors: Hoyun Choi, Sungyeop Lee, B. Kahng, Junghyo Jo

Organizations: CTP and Department of Physics and Astronomy, Seoul National University, Seoul 08826, Korea · Department of Physics and Astronomy, Seoul National University, Seoul 08826, Korea · CCSS, KI for Grid Modernization, Korea Institute of Energy Technology, Naju, Jeonnam 58330, Korea · Department of Physics Education, Seoul National University, Seoul 08826, Korea · 

Abstract

Simulating complex systems governed by coupled ordinary differential equations (ODEs) typically requires explicit governing equations and incurs high computational cost from iterative numerical solvers. We propose the Neural Graph Simulator (NGS), a general-purpose data-driven framework that learns multivariate continuous-time dynamics directly from noisy and incomplete observations, without prior knowledge of the equations. Unlike neural ODE-based approaches that depend on repeated solver evaluations, NGS approximates the state transition integral using elapsed time intervals as direct inputs. This eliminates numerical integration while naturally supporting irregular sampling and heterogeneous time scales. Through its graph network architecture, NGS generalizes to unseen graph structures and larger system sizes, as demonstrated on independently sampled Erdős--Rényi graphs. We evaluate NGS on comprehensive benchmarks covering linear diffusion, nonlinear and chaotic dynamics, systems with stiffness-like behavior, and real-world spatiotemporal datasets. NGS combines competitive accuracy across benchmarks with substantial speedups over numerical solvers in computationally demanding settings. Notably, NGS exhibits strong extrapolation to unseen graph sizes and longer time horizons, and supports non-uniform time steps. These results establish NGS as an efficient and scalable alternative to solver-dependent neural simulators.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Predicting Dynamics of Ultra-Large Complex Systems by Inferring Governing Equations

    Apr 1, 2026Qi Shao, Duxin Chen, Jiawen Chen +5Dynamical SystemsNonlinear System Identification

  2. The Physics Is the Network: Fast, Training-Free Neural Emulation

    Oct 14, 2026Luka Todorovic, Kaushal Gianchandani, Sai RavelaNeural PDE SolversNeural Surrogate Modeling