[论文解读] Manifold-Orthogonal Dual-spectrum Extrapolation for Parameterized Physics-Informed Neural Networks

Zhangyong Liang, Ji Zhang|arXiv (Cornell University)|Mar 14, 2026

Model Reduction and Neural Networks被引用 0

一句话总结

MODE 是一个以物理为基础的参数化PINN微调机制，通过将演化解耦为主谱混合、残差谱觉醒与仿射伽辽金 unlocking，克服基于SVD的局限性，在最小的参数成本下实现对OOD的更优泛化。

ABSTRACT

Physics-informed neural networks (PINNs) have achieved notable success in modeling dynamical systems governed by partial differential equations (PDEs). To avoid computationally expensive retraining under new physical conditions, parameterized PINNs (P$^2$INNs) commonly adapt pre-trained operators using singular value decomposition (SVD) for out-of-distribution (OOD) regimes. However, SVD-based fine-tuning often suffers from rigid subspace locking and truncation of important high-frequency spectral modes, limiting its ability to capture complex physical transitions. While parameter-efficient fine-tuning (PEFT) methods appear to be promising alternatives, applying conventional adapters such as LoRA to P$^2$INNs introduces a severe Pareto trade-off, as additive updates increase parameter overhead and disrupt the structured physical manifolds inherent in operator representations. To address these limitations, we propose Manifold-Orthogonal Dual-spectrum Extrapolation (MODE), a lightweight micro-architecture designed for physics operator adaptation. MODE decomposes physical evolution into complementary mechanisms including principal-spectrum dense mixing that enables cross-modal energy transfer within frozen orthogonal bases, residual-spectrum awakening that activates high-frequency spectral components through a single trainable scalar, and affine Galilean unlocking that explicitly isolates spatial translation dynamics. Experiments on challenging PDE benchmarks including the 1D Convection--Diffusion--Reaction equation and the 2D Helmholtz equation demonstrate that MODE achieves strong out-of-distribution generalization while preserving the minimal parameter complexity of native SVD and outperforming existing PEFT-based baselines.

研究动机与目标

• 推动在不从零重新训练的前提下，参数化PINN对OOD物理参数的高效适应需求；
• 识别应用于PDE求解的PINN的基于SVD的微调中的基本瓶颈；
• 提出一种新型微架构（MODE），将物理演化解耦为主谱混合、残谱觉醒和仿射伽辽金unlocking；
• 证明MODE在最小空间复杂度下实现帕累托占优的性能并提升OOD泛化能力。

提出的方法

• 将带有预训练P2INN的参数化PDE求解问题，通过SVD将权重分解为主谱和残谱来建模；
• 引入MODE，具有一组可训练的小参数：一个用于主谱混合的密集矩阵Phi，一个用于觉醒残谱的标量tau，以及一个用于仿射伽辽金unlocking的偏置漂移Delta b；
• 构造等效前向算子，将冻结的正交基与Phi组合，放大残谱的tau并平移偏置，从而避免高维残谱存储；
• 推导无残差的代数重构以避免内存爆炸，提供高效前向传播，重复使用预训练权重；
• 从理论角度论证MODE消除了子空间锁定，保留高频模态，并解耦仿射平移以提升优化与泛化。

实验结果

研究问题

• RQ1 MODE 是否能够克服常规PEFT方法在将P2INN适配到OOD PDE参数时的帕累托劣势？
• RQ2 如何将物理演化解耦为主谱、残谱和仿射分量以在不膨胀参数量的情况下改进外推能力？
• RQ3 MODE 是否在保留本地SVD的空间复杂度同时提升对对流-扩散-反应和Helmholtz型PDE的OOD泛化？
• RQ4 是否能在一个可训练的标量下重新激活残差字典而不增加模型规模？
• RQ5 在物理信息上下文中现有PEFT方法的理论局限性是什么，MODE如何应对它们？

主要发现

• MODE 通过将本地SVD的原生空间内存占用最小化，同时在OOD保真度上超越PEFT基线，从而实现绝对帕累托支配。
• 主谱密集混合在冻结基底中实现跨模态的能量传递，参数成本较小。
• 残谱觉醒使用一个可训练标量动态触发高频模态。
• 仿射伽辽金 unlocking 通过独立的偏置漂移来隔离空间平移，简化优化。
• 与原生SVD及领先的PEFT相比，MODE在具有挑战性的1D对流-扩散-反应与2D Helmholtz型PDE上提供更好的外推能力。