A Residual Guided strategy with Generative Adversarial Networks in training Physics-Informed Transformer Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ziyang, Zhang, Feifan, Tang, Weidong, Shi, Lei, Chen, Tailai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912997022105600
author Zhang, Ziyang
Zhang, Feifan
Tang, Weidong
Shi, Lei
Chen, Tailai
author_facet Zhang, Ziyang
Zhang, Feifan
Tang, Weidong
Shi, Lei
Chen, Tailai
contents Nonlinear partial differential equations (PDEs) are pivotal in modeling complex physical systems, yet traditional Physics-Informed Neural Networks (PINNs) often struggle with unresolved residuals in critical spatiotemporal regions and violations of temporal causality. To address these limitations, we propose a novel Residual Guided Training strategy for Physics-Informed Transformer via Generative Adversarial Networks (GAN). Our framework integrates a decoder-only Transformer to inherently capture temporal correlations through autoregressive processing, coupled with a residual-aware GAN that dynamically identifies and prioritizes high-residual regions. By introducing a causal penalty term and an adaptive sampling mechanism, the method enforces temporal causality while refining accuracy in problematic domains. Extensive numerical experiments on the Allen-Cahn, Klein-Gordon, and Navier-Stokes equations demonstrate significant improvements, achieving relative MSE reductions of up to three orders of magnitude compared to baseline methods. This work bridges the gap between deep learning and physics-driven modeling, offering a robust solution for multiscale and time-dependent PDE systems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00855
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Residual Guided strategy with Generative Adversarial Networks in training Physics-Informed Transformer Networks
Zhang, Ziyang
Zhang, Feifan
Tang, Weidong
Shi, Lei
Chen, Tailai
Machine Learning
Computational Engineering, Finance, and Science
Fluid Dynamics
Nonlinear partial differential equations (PDEs) are pivotal in modeling complex physical systems, yet traditional Physics-Informed Neural Networks (PINNs) often struggle with unresolved residuals in critical spatiotemporal regions and violations of temporal causality. To address these limitations, we propose a novel Residual Guided Training strategy for Physics-Informed Transformer via Generative Adversarial Networks (GAN). Our framework integrates a decoder-only Transformer to inherently capture temporal correlations through autoregressive processing, coupled with a residual-aware GAN that dynamically identifies and prioritizes high-residual regions. By introducing a causal penalty term and an adaptive sampling mechanism, the method enforces temporal causality while refining accuracy in problematic domains. Extensive numerical experiments on the Allen-Cahn, Klein-Gordon, and Navier-Stokes equations demonstrate significant improvements, achieving relative MSE reductions of up to three orders of magnitude compared to baseline methods. This work bridges the gap between deep learning and physics-driven modeling, offering a robust solution for multiscale and time-dependent PDE systems.
title A Residual Guided strategy with Generative Adversarial Networks in training Physics-Informed Transformer Networks
topic Machine Learning
Computational Engineering, Finance, and Science
Fluid Dynamics
url https://arxiv.org/abs/2508.00855