Saved in:
Bibliographic Details
Main Authors: Zhang, Zhizhou, Wu, Youjia, Zhang, Kaixuan, Wang, Yanjia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.25788
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918151472545792
author Zhang, Zhizhou
Wu, Youjia
Zhang, Kaixuan
Wang, Yanjia
author_facet Zhang, Zhizhou
Wu, Youjia
Zhang, Kaixuan
Wang, Yanjia
contents Industrial design evaluation often relies on high-fidelity simulations of governing partial differential equations (PDEs). While accurate, these simulations are computationally expensive, making dense exploration of design spaces impractical. Operator learning has emerged as a promising approach to accelerate PDE solution prediction; however, its effectiveness is often limited by the scarcity of labeled physics-based data. At the same time, large numbers of geometry-only candidate designs are readily available but remain largely untapped. We propose a two-stage framework to better exploit this abundant, physics-agnostic resource and improve supervised operator learning under limited labeled data. In Stage 1, we pretrain an autoencoder on a geometry reconstruction task to learn an expressive latent representation without PDE labels. In Stage 2, the neural operator is trained in a standard supervised manner to predict PDE solutions, using the pretrained latent embeddings as inputs instead of raw point clouds. Transformer-based architectures are adopted for both the autoencoder and the neural operator to handle point cloud data and integrate both stages seamlessly. Across four PDE datasets and three state-of-the-art transformer-based neural operators, our approach consistently improves prediction accuracy compared to models trained directly on raw point cloud inputs. These results demonstrate that representations from physics-agnostic pretraining provide a powerful foundation for data-efficient operator learning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25788
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining
Zhang, Zhizhou
Wu, Youjia
Zhang, Kaixuan
Wang, Yanjia
Machine Learning
Industrial design evaluation often relies on high-fidelity simulations of governing partial differential equations (PDEs). While accurate, these simulations are computationally expensive, making dense exploration of design spaces impractical. Operator learning has emerged as a promising approach to accelerate PDE solution prediction; however, its effectiveness is often limited by the scarcity of labeled physics-based data. At the same time, large numbers of geometry-only candidate designs are readily available but remain largely untapped. We propose a two-stage framework to better exploit this abundant, physics-agnostic resource and improve supervised operator learning under limited labeled data. In Stage 1, we pretrain an autoencoder on a geometry reconstruction task to learn an expressive latent representation without PDE labels. In Stage 2, the neural operator is trained in a standard supervised manner to predict PDE solutions, using the pretrained latent embeddings as inputs instead of raw point clouds. Transformer-based architectures are adopted for both the autoencoder and the neural operator to handle point cloud data and integrate both stages seamlessly. Across four PDE datasets and three state-of-the-art transformer-based neural operators, our approach consistently improves prediction accuracy compared to models trained directly on raw point cloud inputs. These results demonstrate that representations from physics-agnostic pretraining provide a powerful foundation for data-efficient operator learning.
title From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining
topic Machine Learning
url https://arxiv.org/abs/2509.25788