Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CATO: Charted Attention for Neural PDE Operators

About

Neural operators have emerged as powerful data-driven solvers for PDEs, offering substantial acceleration over classical numerical methods. However, existing transformer-based operators still face critical challenges when modeling PDEs on complex geometries: directly processing over massive mesh points is computationally expensive, while operating in raw discretization coordinates may obscure the intrinsic geometry where physical interactions are more naturally expressed. To address these limitations, we introduce the Charted Axial Transformer Operator (CATO), a geometry-adaptive and derivative-aware neural operator for PDEs on general geometries. Instead of applying attention directly in the physical coordinate system, CATO learns a continuous latent chart that maps mesh coordinates into a learned chart space, where chart-conditioned axial attention efficiently captures long-range dependencies with reduced computational cost. In addition, CATO introduces a derivative-aware physics loss for steady-state PDEs that jointly supervises solution values, mesh-consistent gradients, and an auxiliary flux-like field, improving physical fidelity and reducing oversmoothing. We further provide a theoretical approximation result showing that, under a favorable chart, charted axial attention can represent low-rank axial solution operators with controlled error, and that small chart perturbations induce bounded approximation degradation. CATO achieves the best performance across all evaluated datasets, yielding an average improvement of approximately 26.76\% over the strongest competing baselines while reducing the number of parameters by 81.98\%. These results highlight the effectiveness of learning geometry-adaptive charts and derivative-aware physical supervision for accurate and efficient PDE operator learning.

Chun-Wun Cheng, Sifan Wang, Carola-Bibiane Sch\"onlieb, Angelica I. Aviles-Rivero• 2026

Related benchmarks

TaskDatasetResultRank
PDE solvingDarcy Regular Grid (test)
Relative L2 Error0.0042
41
PDE solvingNavier-Stokes Regular Grid (test)
Relative L2 Error0.0319
41
PDE solvingAirfoil Structured Mesh (test)
Relative L2 Error0.0041
38
PDE solvingPipe Structured Mesh (test)
Relative L2 Error0.0038
38
PDE solvingPlasticity Structured Mesh (test)
Relative L2 Error5.00e-4
23
PDE solvingElasticity Point Cloud (test)
Relative L2 Error0.7
20
Showing 6 of 6 rows

Other info

Follow for update