This paper introduces PDEformer-1, a versatile neural solver capable of simultaneously addressing various partial differential equations (PDEs). With the PDE represented as a computational graph, we facilitate the seamless integration of symbolic and numeric information inherent in a PDE. A graph Transformer and an implicit neural representation (INR) are employed subsequently to generate mesh-free predicted solutions. We generated a dataset with up to three million samples involving diverse one-dimensional PDEs to pretrain our model. Compared with baseline models trained specifically on benchmark datasets, our pretrained model achieves comparable accuracy via zero-shot inference, and the advantage expands after finetuning. For PDEs new or unseen in the pretraining stage, our model can adapt quickly by finetuning on a relatively small set of examples from the target equation. Additionally, PDEformer-1 demonstrates promising results in the inverse problem of PDE scalar coefficient recovery and coefficient field recovery.
@article{arxiv.2407.06664,
title = {PDEformer-1: A Foundation Model for One-Dimensional Partial Differential Equations},
author = {Zhanhong Ye and Xiang Huang and Leheng Chen and Zining Liu and Bingyang Wu and Hongsheng Liu and Zidong Wang and Bin Dong},
journal= {arXiv preprint arXiv:2407.06664},
year = {2025}
}