mlsanityData to 7 Oct 2026

PIBNet: a Physics-Inspired Boundary Network for Multiple Scattering Simulations

arXiv 2512.02049 ↗First posted 26 Nov 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The boundary element method (BEM) provides an efficient numerical framework for solving multiple scattering problems in unbounded homogeneous domains, since it reduces the discretization to the domain boundaries, thereby condensing the computational complexity. The procedure first consists in determining the solution trace on the boundaries of the domain by solving a boundary integral equation, after which the volumetric solution can be recovered at low computational cost with a boundary integral representation. As the first step of the BEM represents the main computational bottleneck, we introduce PIBNet, a learning-based approach designed to approximate the solution trace. The method leverages a physics-inspired graph-based strategy to model obstacles and their long-range interactions efficiently. Then, we introduce a novel multiscale graph neural network architecture for simulating the multiple scattering. To train and evaluate our network, we present a benchmark consisting of several datasets of different types of multiple scattering problems. The results indicate that our approach not only surpasses existing state-of-the-art learning-based methods on the considered tasks but also exhibits superior generalization to settings with an increased number of obstacles. github.com/ENSTA-U2IS-AI/pibnet

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 26 Nov 2025.

Builds on

29 of 46 references.

References · 29

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  4. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  5. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  6. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 722
  7. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  8. 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 416
  9. 2020Multipole Graph Neural Operator for Parametric Partial Differential Equationscited by 343
  10. 2023GNOT: A General Neural Operator Transformer for Operator Learningcited by 321
  11. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 299
  12. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 293
17 more
  1. 2022Transformer for Partial Differential Equations' Operator Learningcited by 270
  2. 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 219
  3. 2022MultiScale MeshGraphNetscited by 94
  4. 2025Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometriescited by 89
  5. 2023Improved Operator Learning by Orthogonal Attentioncited by 58
  6. 2025Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary Domainscited by 56
  7. 2023Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformerscited by 54
  8. 2025AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformerscited by 49
  9. 2024CViT: Continuous Vision Transformer for Operator Learningcited by 47
  10. 2022Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNcited by 43
  11. 2024AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fieldscited by 38
  12. 2025Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systemscited by 21
  13. 2022BI-GreenNet: Learning Green's functions by boundary integral networkcited by 13
  14. 2023Learning Only On Boundaries: a Physics-Informed Neural operator for Solving Parametric Partial Differential Equations in Complex Geometriescited by 12
  15. 2023Multiscale Neural Operators for Solving Time-Independent PDEscited by 5
  16. 2025Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physicscited by 5
  17. 2024Solving Partial Differential Equations in Different Domains by Operator Learning method Based on Boundary Integral Equationscited by 4

Built on by

Not cited yet.