AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training

• URL: http://arxiv.org/abs/2605.15793v1
• Date: Fri, 15 May 2026 09:50:34 GMT
• Title: AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
• Abstract summary: We propose to transform complex and diverse solution operators into simpler, better-aligned forms that are easier to model jointly.<n>We instantiate this idea as AOT-POT (adaptive operator-transformation for pre-training operator transformer), which expands hidden representations into multiple parallel streams.<n>AOT-POT achieves state-of-the-art performance on 12 PDE benchmarks with only 3% additional parameters, reducing relative L2 error by up to 77.6% (40.9% on average)
• Score: 50.28798360093496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-training neural operators on diverse partial differential equation (PDE) datasets has emerged as a promising direction for building general-purpose surrogate models in scientific machine learning. However, the inherent complexity and structural diversity of PDE solution operators make multi-PDE pre-training fundamentally challenging. Existing methods mainly address this by increasing model capacity, while leaving the target solution operators unchanged. Inspired by classical numerical analysis, we instead propose to transform complex and diverse solution operators into simpler, better-aligned forms that are easier to model jointly. Since the optimal transformation varies across PDE types, it must be adaptive and input-dependent, allowing a single neural operator to approximate an entire family of operators. We instantiate this idea as AOT-POT (adaptive operator-transformation for pre-training operator transformer), which expands hidden representations into multiple parallel streams, adaptively aggregates and redistributes them before and after each sub-layer, and mixes streams through Sinkhorn-projected doubly stochastic matrices for stable training. These mechanisms together reshape diverse solution operators into a unified form that can be effectively modeled by a single architecture. Empirically, AOT-POT achieves state-of-the-art performance on 12 PDE benchmarks with only 3\% additional parameters, reducing relative L2 error by up to 77.6\% (40.9\% on average). Fine-tuning AOT-POT further reduces L2 error by up to 92\% on in-domain PDEs and 89\% on out-of-domain PDEs (unseen types during pre-training), demonstrating that adaptive operator transformation is an effective and complementary direction for advancing PDE foundation models beyond simply scaling model capacity.

Related papers

• Equation Recast for Canonical Operator Learning Across Parametric PDEs [59.44573033543284]
  We introduce equation recast, which reformulates parametric operator learning as the learning of a single canonical operator.<n>In high-fidelity tokamak simulations for nuclear fusion, the framework unifies electron-temperature data across four device geometries.
  arXiv  Detail & Related papers  (2026-09-02T13:15:50Z)
• Operator Boosting Produces Pareto-Efficient PDE Surrogates [0.0]
  Operator Boosting is a stagewise residual-learning framework for constructing compact neural-operator surrogates directly.<n>We compare boosted stacks against full-size monolithic PDE benchmarks from PDEBench, APEBench, and The Well.<n>Across 30 dataset-architecture pairs, 21 show positive mean accuracy gains and 17 have positive confidence intervals, while all boosted stacks reduce trainable parameter count by approximately 72-95%.
  arXiv  Detail & Related papers  (2026-06-16T03:20:44Z)
• Variational Entropic Optimal Transport [67.76725267984578]
  We propose Variational Entropic Optimal Transport (VarEOT) for domain translation problems.<n>VarEOT is based on an exact variational reformulation of the log-partition $log mathbbE[exp(cdot)$ as a tractable generalization over an auxiliary positive normalizer.<n> Experiments on synthetic data and unpaired image-to-image translation demonstrate competitive or improved translation quality.
  arXiv  Detail & Related papers  (2026-02-02T15:48:44Z)
• Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations [65.80144621950981]
  We build on Wiener chaos expansions (WCE) to design neural operator (NO) architectures for SPDEs and SDEs.<n>We show that WCE-based neural operators provide a practical and scalable way to learn SDE/SPDE solution operators.
  arXiv  Detail & Related papers  (2026-01-03T00:59:25Z)
• Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs [16.38975732337055]
  TGPS is a machine learning solver for partial differential equations.<n>It reduces the task to learning a collection of one-dimensional GPs.<n>It achieves superior accuracy and efficiency compared to existing approaches.
  arXiv  Detail & Related papers  (2025-10-15T17:23:21Z)
• Scale-Consistent Learning for Partial Differential Equations [79.48661503591943]
  We propose a data augmentation scheme based on scale-consistency properties of PDEs.<n>We then design a scale-informed neural operator that can model a wide range of scales.<n>With scale-consistency, the model trained on $Re$ of 1000 can generalize to $Re$ ranging from 250 to 10000.
  arXiv  Detail & Related papers  (2025-07-24T21:29:52Z)
• Self-supervised Pretraining for Partial Differential Equations [0.0]
  We describe a novel approach to building a neural PDE solver leveraging recent advances in transformer based neural network architectures. Our model can provide solutions for different values of PDE parameters without any need for retraining the network.
  arXiv  Detail & Related papers  (2024-07-03T16:39:32Z)
• UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation [25.063470461409686]
  UPS embeds different PDEs into a shared representation space and processes them using a F-transformer architecture. Cross-modal UPS achieves state-of-the-art results on a wide range of 1D and 2D PDE families from PDEBench, outperforming existing unified models using 4 times less data transfer and 26 times less compute.
  arXiv  Detail & Related papers  (2024-03-11T22:00:39Z)
• DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training [87.90342423839876]
  We present a new auto-regressive denoising pre-training strategy, which allows for more stable and efficient pre-training on PDE data. We train our PDE foundation model with up to 0.5B parameters on 10+ PDE datasets with more than 100k trajectories.
  arXiv  Detail & Related papers  (2024-03-06T08:38:34Z)
• Neural Partial Differential Equations with Functional Convolution [30.35306295442881]
  We present a lightweighted neural PDE representation to discover the hidden structure and predict the solution of different nonlinear PDEs. We leverage the prior of translational similarity'' of numerical PDE differential operators to drastically reduce the scale of learning model and training data.
  arXiv  Detail & Related papers  (2023-03-10T04:25:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.