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

GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems

About

Operator learning for partial differential equations (PDEs) on arbitrary geometries builds fast neural surrogates for large-scale simulation. Although recent geometry-adaptive neural operators have made substantial progress, they are mainly designed for forward problems in which inputs and outputs share the same spatial domain. This limits their applicability for boundary value problems (BVPs) and inverse problems, where inputs and outputs may live on different domains. We introduce the Geometry-Adaptive Integral Autoencoder (GAIA), an operator learning model that encodes the domain boundary and the interior field distribution into geometry tokens, and conditions integral transform layers on these tokens via cross-attention, allowing the kernel to adapt locally to geometric features. This yields a single architecture for forward (including BVPs) and inverse problems on arbitrary domains in one pass, without retraining, iterative optimization, or graph construction. We evaluate GAIA on seven 2D and 3D benchmarks, four of which are new or substantially extended benchmarks for inverse problems and BVP: electrical impedance tomography, optical tomography, 3D Darcy flow on varying geometries, and a modified setting of Poisson BVP on mechanical components benchmark (MCB). GAIA sets new state-of-the-art results on every inverse and BVP task, reducing median relative $L^2$ error by 64% on airfoil flow reconstruction and 27% on EIT relative to the next best amortized method, and outperforming all baselines on every shape category of MCB. On other forward problems, GAIA is competitive with specialized solvers while maintaining stable accuracy across point resolutions on which transformer-based baselines degrade.

Meenakshi Krishnan, Pranav Pulijala, Ke Chen, Haizhao Yang, Ramani Duraiswami• 2026

Related benchmarks

TaskDatasetResultRank
Forward PDE solvingElasticity--
44
Forward problemPOISSON GAUSS
Median Relative L2 Error0.71
5
Inverse ProblemsEIT
Median Relative L2 Error0.71
5
Inverse ProblemsOT
Median Relative L2 Error1.41
5
Inverse ProblemsAirfoil
Median Relative L2 Error0.58
5
Forward problem3D-Darcy
Median Relative L2 Error1.11
5
3D Poisson Boundary Value Problem (BVP)Mechanical Components Benchmark (MCB) (test)
Fitting Error Rate10.15
4
Inverse ProblemEIT
Latency (ms)15.78
4
Showing 8 of 8 rows

Other info

Follow for update