Disentangling Attention in Deep Operator Learning: A Controlled Study of Data-Driven and Physics-Informed Architectures

• URL: http://arxiv.org/abs/2609.04407v1
• Date: Thu, 03 Sep 2026 19:17:01 GMT
• Title: Disentangling Attention in Deep Operator Learning: A Controlled Study of Data-Driven and Physics-Informed Architectures
• Abstract summary: Attention mechanisms have been introduced into neural operators, but most studies change several architectural components at once.<n>This work presents a controlled and systematic study of five deep operator network (DeepONet) variants with distinct attention mechanisms, trained under both data-driven and physics-informed regimes.
• Score: 0.25489046505746704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural operators learn mappings between input functions and complete PDE solution fields, enabling forward evaluations of new problem instances orders of magnitude faster than conventional numerical solvers. Attention mechanisms have recently been introduced into neural operators, but most studies change several architectural components at once, making it difficult to identify what actually improves accuracy. This work presents a controlled and systematic study of five deep operator network (DeepONet) variants with distinct attention mechanisms, trained under both data-driven and physics-informed regimes, to isolate the effects of cross-attention, self-attention, tokenization, and attention depth. We evaluate them on a source-driven transient one-dimensional nonlinear diffusion-reaction equation, a transient one-dimensional viscous Burgers equation with variable initial conditions, and a two-dimensional Poisson heat-conduction problem with heterogeneous source fields. Per-sensor tokenization with cross-attention reduces the mean relative L_2 error of the classical DeepONet in all benchmark-training combinations by factors of 2.4-28.0, while the best attention configurations reach 3.5-32.3. Branch self-attention paired only with dot-product fusion is inconsistent, degrading the one-dimensional problems while helping the more complex two-dimensional source field; added on top of cross-attention it improves all six cases, though by less than cross-attention fusion alone. Global pre-mixing provides no consistent benefit. Increasing cross-attention depth further improves accuracy, but with diminishing returns and a substantially higher cost under physics-informed training. Overall, query-dependent cross-attention is the most reliable mechanism, whereas branch self-attention is most useful for large, spatially complex functional inputs.

Related papers

• ShortcutBreaker: Low-Rank Noisy Bottleneck with Global Perturbation Attention for Multi-Class Unsupervised Anomaly Detection [59.89803740308262]
  ShortcutBreaker is a novel unified feature-reconstruction framework for MUAD tasks.<n>It features two key innovations to address the issue of shortcuts.<n>The proposed method achieves a remarkable image-level AUROC of 99.8%, 98.9%, 90.6%, and 87.8% on four datasets.
  arXiv  Detail & Related papers  (2025-10-21T06:51:30Z)
• When Network Architecture Meets Physics: Deep Operator Learning for Coupled Multiphysics [0.36651088217486427]
  We present a comprehensive evaluation of DeepONet variants across three regimes: single-physics, weakly coupled, and strongly coupled multiphysics systems.<n>We consider a reaction-diffusion equation with dual spatial inputs, a nonlinear thermo-electrical problem with bidirectional coupling through temperature-dependent conductivity, and a viscoplastic thermo-mechanical model of steel solidification governed by transient phase-driven interactions.<n>Our results demonstrate that architectural alignment with physical coupling is crucial, whereas multi-branch encodings offer advantages for decoupled or single-physics problems.
  arXiv  Detail & Related papers  (2025-07-04T15:36:15Z)
• USAD: End-to-End Human Activity Recognition via Diffusion Model with Spatiotemporal Attention [8.061018589897277]
  Human activity recognition is a task that finds broad applications in health monitoring, safety protection, and sports analysis.<n>Despite proliferating research, human activity recognition still faces key challenges, including the scarcity of labeled samples for rare activities.<n>This paper proposes a comprehensive optimization approach centered on multi-attention interaction mechanisms.
  arXiv  Detail & Related papers  (2025-07-03T17:38:44Z)
• Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free [81.65559031466452]
  We conduct experiments to investigate gating-augmented softmax attention variants.<n>We find that a simple modification-applying a head-specific sigmoid gate after the Scaled Dot-Product Attention (SDPA)-consistently improves performance.
  arXiv  Detail & Related papers  (2025-05-10T17:15:49Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture.<n>We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery [25.75410883895742]
  We propose a novel neural operator architecture based on the attention mechanism, which we coin Nonlocal Attention Operator (NAO) NAO can address ill-posedness and rank deficiency in inverse PDE problems by encoding regularization and achieving generalizability.
  arXiv  Detail & Related papers  (2024-08-14T05:57:56Z)
• AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios [51.94807626839365]
  We propose the attention-inspired numerical solver (AttNS) to solve differential equations due to limited data.<n>AttNS is inspired by the effectiveness of attention modules in Residual Neural Networks (ResNet) in enhancing model generalization and robustness.
  arXiv  Detail & Related papers  (2023-02-05T01:39:21Z)
• Improved generalization with deep neural operators for engineering systems: Path towards digital twin [0.4551615447454769]
  We evaluate the capabilities of Deep Operator Networks (DeepONets), an ONets implementation using a branch/trunk architecture. DeepONets can accurately learn the solution operators, achieving prediction accuracy scores above 0.96 for the ODE and diffusion problems. More importantly, when evaluated on unseen scenarios (zero shot feature), the trained models exhibit excellent generalization ability.
  arXiv  Detail & Related papers  (2023-01-17T04:57:31Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• Choose a Transformer: Fourier or Galerkin [0.0]
  We apply the self-attention from the state-of-the-art Transformer in Attention Is All You Need to a data-driven operator learning problem. We show that softmax normalization in the scaled dot-product attention is sufficient but not necessary, and have proved the approximation capacity of a linear variant as a Petrov-Galerkin projection. We present three operator learning experiments, including the viscid Burgers' equation, an interface Darcy flow, and an inverse interface coefficient identification problem.
  arXiv  Detail & Related papers  (2021-05-31T14:30:53Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)

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.