Global weight deep equilibrium attention for numerical simulations on unstructured meshes

Abstract Graph-based neural networks have emerged as efficient and versatile surrogates for mesh-based numerical simulations. However, achieving high predictive accuracy remains challenging due to over-smoothing, under-reaching during message passing, and disregard for mesh connectivity. To address this, we propose Global Weight Deep Equilibrium Attention (GDEA). GDEA constructs a sparse global weight matrix from mesh connectivity via the direct stiffness method, introducing an inductive bias toward diagonal dominance. We apply the resulting matrix iteratively until convergence, allowing information to propagate globally without adding extra message-passing layers. We formulate the iterative process as a Deep Equilibrium Model (DEQ) to reduce memory consumption, and we use Anderson acceleration to speed convergence. Extensive experiments across multiple numerical simulation datasets, including the newly introduced Deformed ABC dataset with diverse geometries, materials, and boundary conditions, demonstrate that GDEA outperforms other methods on Deformed ABC while remaining competitive on established benchmarks. An accurate surrogate model that can handle diverse design configurations can facilitate efficient early-stage design exploration.

Authors

Institutions

Publication Details

Journal
Communications Engineering
Published
2026-11-14
DOI
https://doi.org/10.1038/s44172-026-00816-z
Primary Topic
Model Reduction and Neural Networks
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Global weight deep equilibrium attention for numerical simulations on unstructured meshes

Junghun Lee, Conrad Tucker
2 links
Communications Engineering
Model Reduction and Neural Networks
article

Global weight deep equilibrium attention for numerical simulations on unstructured meshes

Junghun Lee, Conrad Tucker
article en

Abstract

Abstract Graph-based neural networks have emerged as efficient and versatile surrogates for mesh-based numerical simulations. However, achieving high predictive accuracy remains challenging due to over-smoothing, under-reaching during message passing, and disregard for mesh connectivity. To address this, we propose Global Weight Deep Equilibrium Attention (GDEA). GDEA constructs a sparse global weight matrix from mesh connectivity via the direct stiffness method, introducing an inductive bias toward diagonal dominance. We apply the resulting matrix iteratively until convergence, allowing information to propagate globally without adding extra message-passing layers. We formulate the iterative process as a Deep Equilibrium Model (DEQ) to reduce memory consumption, and we use Anderson acceleration to speed convergence. Extensive experiments across multiple numerical simulation datasets, including the newly introduced Deformed ABC dataset with diverse geometries, materials, and boundary conditions, demonstrate that GDEA outperforms other methods on Deformed ABC while remaining competitive on established benchmarks. An accurate surrogate model that can handle diverse design configurations can facilitate efficient early-stage design exploration.

Communications Engineering
Carnegie Mellon University (US)
Model Reduction and Neural Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon