mlsanityData to 7 Oct 2026

Scalable and Consistent Graph Neural Networks for Distributed Mesh-based Data-driven Modeling

arXiv 2410.01657 ↗First posted 2 Oct 2024cs.DC cs.LG physics.comp-phcited by 2

Not on the map. Why?

Abstract (arXiv)

This work develops a distributed graph neural network (GNN) methodology for mesh-based modeling applications using a consistent neural message passing layer. As the name implies, the focus is on enabling scalable operations that satisfy physical consistency via halo nodes at sub-graph boundaries. Here, consistency refers to the fact that a GNN trained and evaluated on one rank (one large graph) is arithmetically equivalent to evaluations on multiple ranks (a partitioned graph). This concept is demonstrated by interfacing GNNs with NekRS, a GPU-capable exascale CFD solver developed at Argonne National Laboratory. It is shown how the NekRS mesh partitioning can be linked to the distributed GNN training and inference routines, resulting in a scalable mesh-based data-driven modeling workflow. We study the impact of consistency on the scalability of mesh-based GNNs, demonstrating efficient scaling in consistent GNNs for up to O(1B) graph nodes on the Frontier exascale supercomputer.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 2 Oct 2024.

Builds on

24 of 37 references.

References · 24

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  4. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  5. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  6. 2021Machine learning accelerated computational fluid dynamicscited by 461
  7. 2020Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Predictioncited by 137
  8. 2023Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behaviorcited by 128
  9. 2020Transformers for Modeling Physical Systemscited by 105
  10. 2022MultiScale MeshGraphNetscited by 94
  11. 2018Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systemscited by 54
  12. 2021Simulating Continuum Mechanics with Multi-Scale Graph Neural Networkscited by 39
12 more
  1. 2022MAgNET: A Graph U-Net Architecture for Mesh-Based Simulationscited by 26
  2. 2023Multiscale Graph Neural Network Autoencoders for Interpretable Scientific Machine Learningcited by 18
  3. 2021Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systemscited by 16
  4. 2022A Finite Element-Inspired Hypergraph Neural Network: Application to Fluid Dynamics Simulationscited by 14
  5. 2024Multiscale graph neural networks with adaptive mesh refinement for accelerating mesh-based simulationscited by 12
  6. 2023Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challengescited by 9
  7. 2021NekRS, a GPU-Accelerated Spectral Element Navier-Stokes Solvercited by 8
  8. 2023Importance of equivariant and invariant symmetries for fluid flow modelingcited by 5
  9. 2023Multi-GPU Approach for Training of Graph ML Models on large CFD Meshescited by 4
  10. 2023In Situ Framework for Coupling Simulation and Machine Learning with Application to CFDcited by 2
  11. 2024Sampling-based Distributed Training with Message Passing Neural Networkcited by 2
  12. 2024Combining Machine Learning with Computational Fluid Dynamics using OpenFOAM and SmartSimcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Learning Effective Dynamics across Spatio-Temporal Scales of Complex Flowscited by 2
  2. 2025A Mesh-Adaptive Hypergraph Neural Network for Unsteady Flow Around Oscillating and Rotating Structurescited by 0