Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs

arXiv:2602.02788v14 citations
Originality Highly original
AI Analysis

This addresses the challenge of geometry generalization in neural PDEs for science and engineering applications, representing a novel method rather than incremental progress.

The paper tackles the problem of developing physics foundation models that preserve structure and accuracy when solving PDEs on unseen geometries, introducing Geo-NeW which achieves state-of-the-art performance on steady-state PDE benchmarks and significantly improves over baselines on out-of-distribution geometries.

We aim to develop physics foundation models for science and engineering that provide real-time solutions to Partial Differential Equations (PDEs) which preserve structure and accuracy under adaptation to unseen geometries. To this end, we introduce General-Geometry Neural Whitney Forms (Geo-NeW): a data-driven finite element method. We jointly learn a differential operator and compatible reduced finite element spaces defined on the underlying geometry. The resulting model is solved to generate predictions, while exactly preserving physical conservation laws through Finite Element Exterior Calculus. Geometry enters the model as a discretized mesh both through a transformer-based encoding and as the basis for the learned finite element spaces. This explicitly connects the underlying geometry and imposed boundary conditions to the solution, providing a powerful inductive bias for learning neural PDEs, which we demonstrate improves generalization to unseen domains. We provide a novel parameterization of the constitutive model ensuring the existence and uniqueness of the solution. Our approach demonstrates state-of-the-art performance on several steady-state PDE benchmarks, and provides a significant improvement over conventional baselines on out-of-distribution geometries.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes