Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

• URL: http://arxiv.org/abs/2511.08185v1
• Date: Wed, 12 Nov 2025 01:45:25 GMT
• Title: Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
• Authors: Tai Hoang, Alessandro Trenta, Alessio Gravina, Niklas Freymuth, Philipp Becker, Davide Bacciu, Gerhard Neumann,
• Abstract summary: Recent Graph Neural Simulators (GNSs) accelerate simulations by learning dynamics on graph-structured data.<n>We propose Information-preserving Graph Neural Simulators (IGNS), a graph-based neural simulator built on the principles of Hamiltonian dynamics.<n>IGNS consistently outperforms state-of-the-art GNSs, achieving higher accuracy and stability under challenging and complex dynamical systems.
• Score: 71.53370807809296
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning to simulate complex physical systems from data has emerged as a promising way to overcome the limitations of traditional numerical solvers, which often require prohibitive computational costs for high-fidelity solutions. Recent Graph Neural Simulators (GNSs) accelerate simulations by learning dynamics on graph-structured data, yet often struggle to capture long-range interactions and suffer from error accumulation under autoregressive rollouts. To address these challenges, we propose Information-preserving Graph Neural Simulators (IGNS), a graph-based neural simulator built on the principles of Hamiltonian dynamics. This structure guarantees preservation of information across the graph, while extending to port-Hamiltonian systems allows the model to capture a broader class of dynamics, including non-conservative effects. IGNS further incorporates a warmup phase to initialize global context, geometric encoding to handle irregular meshes, and a multi-step training objective to reduce rollout error. To evaluate these properties systematically, we introduce new benchmarks that target long-range dependencies and challenging external forcing scenarios. Across all tasks, IGNS consistently outperforms state-of-the-art GNSs, achieving higher accuracy and stability under challenging and complex dynamical systems.

Related papers

• Graph Network-based Structural Simulator: Graph Neural Networks for Structural Dynamics [40.190675168132124]
  We introduce the Graph Network-based Structural Simulator (GNSS), a GNN framework for surrogate modeling of dynamic structural problems.<n>We evaluate on a case study involving a beam excited by a 50kHz Hanning-modulated pulse.<n>The results show that accurately reproduces the physics of the problem over hundreds of timesteps and generalizes to unseen loading conditions, where existing GNNs fail to converge or deliver meaningful predictions.
  arXiv  Detail & Related papers  (2025-10-29T16:47:24Z)
• MeshODENet: A Graph-Informed Neural Ordinary Differential Equation Neural Network for Simulating Mesh-Based Physical Systems [0.8811039895321705]
  MeshODENet is a general framework that synergizes the spatial reasoning of GNNs with the continuous-time modeling of Neural Ordinary Differential Equations.<n>We show that our approach significantly outperforms baseline models in long-term predictive accuracy and stability.<n>This work presents a powerful and generalizable approach for developing data-driven surrogates to accelerate the analysis and modeling of complex structural systems.
  arXiv  Detail & Related papers  (2025-09-22T22:04:01Z)
• GALDS: A Graph-Autoencoder-based Latent Dynamics Surrogate model to predict neurite material transport [1.104960878651584]
  We propose a Graph-Autoencoder-based Latent Dynamics Surrogate model to streamline the simulation of material transport in neural trees.<n>Our approach achieves mean relative error of 3% with maximum relative error 8% and demonstrates a 10-fold speed improvement compared to previous surrogate model approaches.
  arXiv  Detail & Related papers  (2025-07-15T00:22:00Z)
• Toward accurate RUL and SOH estimation using reinforced graph-based PINNs enhanced with dynamic weights [0.0]
  We propose a framework that combines physics-based supervision with advanced-temporal learning.<n>Q-learning agents dynamically assign weights to physics-informed loss terms, improving generalization across real-time industrial systems.<n>In both RUL and SOH estimation tasks, the proposed method consistently outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2025-07-13T19:49:12Z)
• GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction [4.857364765818477]
  Recent advancements in deep learning, particularly through GraphNNs, have significantly enhanced the accuracy of these forecasts by complex dynamics.<n>However, GraphSparseNet remains a challenge due to their exponential growth in model complexity.<n>This paper introduces GraphSparseNet, a novel framework designed to improve both accuracy and scalability of GNN traffic-based forecasting models.
  arXiv  Detail & Related papers  (2025-02-27T06:51:20Z)
• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework.<n>The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy.<n>Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects [55.02281855589641]
  GausSim is a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels.<n>We leverage continuum mechanics and treat each kernel as a Center of Mass System (CMS) that represents continuous piece of matter.<n>In addition, GausSim incorporates explicit physics constraints, such as mass and momentum conservation, ensuring interpretable results and robust, physically plausible simulations.
  arXiv  Detail & Related papers  (2024-12-23T18:58:17Z)
• Neural Graph Simulator for Complex Systems [0.0]
  We introduce the Neural Graph Simulator (NGS) for simulating time-invariant autonomous systems on graphs. NGS offers significant advantages over numerical solvers by not requiring prior knowledge of governing equations. It demonstrates superior computational efficiency over conventional methods, improving performance by over $105$ times in stiff problems.
  arXiv  Detail & Related papers  (2024-11-14T01:41:00Z)
• DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs [59.434893231950205]
  Dynamic graph learning aims to uncover evolutionary laws in real-world systems. We propose DyG-Mamba, a new continuous state space model for dynamic graph learning. We show that DyG-Mamba achieves state-of-the-art performance on most datasets.
  arXiv  Detail & Related papers  (2024-08-13T15:21:46Z)
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs [65.18780403244178]
  We propose a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE) Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing.
  arXiv  Detail & Related papers  (2022-02-17T02:17:31Z)
• Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
  We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains. Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
  arXiv  Detail & Related papers  (2020-02-21T16:44:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.