Neural Graph Simulator for Complex Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Hoyun, Lee, Sungyeop, Kahng, B., Jo, Junghyo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916479911329792
author Choi, Hoyun
Lee, Sungyeop
Kahng, B.
Jo, Junghyo
author_facet Choi, Hoyun
Lee, Sungyeop
Kahng, B.
Jo, Junghyo
contents Numerical simulation is a predominant tool for studying the dynamics in complex systems, but large-scale simulations are often intractable due to computational limitations. Here, we introduce the Neural Graph Simulator (NGS) for simulating time-invariant autonomous systems on graphs. Utilizing a graph neural network, the NGS provides a unified framework to simulate diverse dynamical systems with varying topologies and sizes without constraints on evaluation times through its non-uniform time step and autoregressive approach. The NGS offers significant advantages over numerical solvers by not requiring prior knowledge of governing equations and effectively handling noisy or missing data with a robust training scheme. It demonstrates superior computational efficiency over conventional methods, improving performance by over $10^5$ times in stiff problems. Furthermore, it is applied to real traffic data, forecasting traffic flow with state-of-the-art accuracy. The versatility of the NGS extends beyond the presented cases, offering numerous potential avenues for enhancement.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09120
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural Graph Simulator for Complex Systems
Choi, Hoyun
Lee, Sungyeop
Kahng, B.
Jo, Junghyo
Machine Learning
Numerical simulation is a predominant tool for studying the dynamics in complex systems, but large-scale simulations are often intractable due to computational limitations. Here, we introduce the Neural Graph Simulator (NGS) for simulating time-invariant autonomous systems on graphs. Utilizing a graph neural network, the NGS provides a unified framework to simulate diverse dynamical systems with varying topologies and sizes without constraints on evaluation times through its non-uniform time step and autoregressive approach. The NGS offers significant advantages over numerical solvers by not requiring prior knowledge of governing equations and effectively handling noisy or missing data with a robust training scheme. It demonstrates superior computational efficiency over conventional methods, improving performance by over $10^5$ times in stiff problems. Furthermore, it is applied to real traffic data, forecasting traffic flow with state-of-the-art accuracy. The versatility of the NGS extends beyond the presented cases, offering numerous potential avenues for enhancement.
title Neural Graph Simulator for Complex Systems
topic Machine Learning
url https://arxiv.org/abs/2411.09120