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

Apr 1, 2026

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

Predicting the behavior of ultra-large complex systems, from climate to biological and technological networks, is a central unsolved challenge. Existing approaches face a fundamental trade-off: equation discovery methods provide interpretability but fail to scale, while neural networks scale but operate as black boxes and often lose reliability over long times. Here, we introduce the Sparse Identification Graph Neural Network, a framework that overcome this divide by allowing to infer the governing equations of large networked systems from data. By defining symbolic discovery as edge-level information, SIGN decouples the scalability of sparse identification from network size, enabling efficient equation discovery even in large systems. SIGN allows to study networks with over 100,000 nodes while remaining robust to noise, sparse sampling, and missing data. Across diverse benchmark systems, including coupled chaotic oscillators, neural dynamics, and epidemic spreading, it recovers governing equations with high precision and sustains accurate long-term predictions. Applied to a data set of time series of temperature measurements in 71,987 sea surface positions, SIGN identifies a compact predictive network model and captures large-scale sea surface temperature conditions up to two years in advance. By enabling equation discovery at previously inaccessible scales, SIGN opens a path toward interpretable and reliable prediction of real-world complex systems.
Sep 3, 2026

Time Without Timesteps: Simulating Coupled Dynamical Systems via Self-Consistency

Numerical simulation of dynamical systems is usually organized as a causal march through time: each state is computed from the previous one. We explore a different formulation for coupled systems. For each subsystem type we train a neural surrogate mapping a full driving trajectory and initial condition directly to a full output trajectory; following classical waveform relaxation, coupled systems are assembled by enforcing self-consistency among these trajectories: simulation becomes a fixed-point problem over complete trajectories rather than a stepwise rollout. On coupled van der Pol oscillators and Hodgkin-Huxley neuron networks, sequential depth becomes the number of solver iterations: 4-10 Newton iterations where the reference integrator takes 1500 steps. The gradient likewise loses its time recursion: it becomes a linear system solved by GMRES at memory independent of solver depth. A single scalar measured from the learned operator, the spectral radius of its Jacobian, predicts in advance where the coupled solve will converge; past that boundary, unrolled backpropagation diverges and a Neumann adjoint fails, while the implicit gradient remains correct to 0.04%. We report where the approach succeeds and where surrogate error degrades it.
Oct 14, 2026

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

Neural emulation need not require learning a substitute for known physics. We investigate PolyNets that couple a continuous-time neural representation of polynomial dynamics with a simple recurrent network for discrete-time integration. When the governing coefficients are known, the resulting tensor graph requires no training and preserves the prescribed numerical scheme while enabling efficient hardware execution and parallel simulation. Using the one-dimensional Korteweg-de Vries equation, we compare PolyNet with CPU and GPU finite-difference Runge-Kutta solvers and three trained neural models: a state-map emulator, a physics-informed predictor, and a learned-tendency integrator. Analytical soliton solutions provide a reference for amplitude and phase errors across grid resolutions, 10^6 dispersively scaled time steps, ensembles of up to 10^4 trajectories, and varying initial amplitudes. PolyNet achieves accuracy comparable to the numerical solvers, including at amplitudes outside the learned models' training conditions. It combines this fidelity with high GPU throughput, approximately constant over the tested resolution range, and favorable ensemble scaling.