English

GITO: Graph-Informed Transformer Operator for Learning Complex Partial Differential Equations

Machine Learning 2025-06-18 v1

Abstract

We present a novel graph-informed transformer operator (GITO) architecture for learning complex partial differential equation systems defined on irregular geometries and non-uniform meshes. GITO consists of two main modules: a hybrid graph transformer (HGT) and a transformer neural operator (TNO). HGT leverages a graph neural network (GNN) to encode local spatial relationships and a transformer to capture long-range dependencies. A self-attention fusion layer integrates the outputs of the GNN and transformer to enable more expressive feature learning on graph-structured data. TNO module employs linear-complexity cross-attention and self-attention layers to map encoded input functions to predictions at arbitrary query locations, ensuring discretization invariance and enabling zero-shot super-resolution across any mesh. Empirical results on benchmark PDE tasks demonstrate that GITO outperforms existing transformer-based neural operators, paving the way for efficient, mesh-agnostic surrogate solvers in engineering applications.

Keywords

Cite

@article{arxiv.2506.13906,
  title  = {GITO: Graph-Informed Transformer Operator for Learning Complex Partial Differential Equations},
  author = {Milad Ramezankhani and Janak M. Patel and Anirudh Deodhar and Dagnachew Birru},
  journal= {arXiv preprint arXiv:2506.13906},
  year   = {2025}
}
R2 v1 2026-07-01T03:20:32.221Z