Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BENO: Boundary-embedded Neural Operators for Elliptic PDEs (2401.09323v1)

Published 17 Jan 2024 in cs.LG

Abstract: Elliptic partial differential equations (PDEs) are a major class of time-independent PDEs that play a key role in many scientific and engineering domains such as fluid dynamics, plasma physics, and solid mechanics. Recently, neural operators have emerged as a promising technique to solve elliptic PDEs more efficiently by directly mapping the input to solutions. However, existing networks typically cannot handle complex geometries and inhomogeneous boundary values present in the real world. Here we introduce Boundary-Embedded Neural Operators (BENO), a novel neural operator architecture that embeds the complex geometries and inhomogeneous boundary values into the solving of elliptic PDEs. Inspired by classical Green's function, BENO consists of two branches of Graph Neural Networks (GNNs) for interior source term and boundary values, respectively. Furthermore, a Transformer encoder maps the global boundary geometry into a latent vector which influences each message passing layer of the GNNs. We test our model extensively in elliptic PDEs with various boundary conditions. We show that all existing baseline methods fail to learn the solution operator. In contrast, our model, endowed with boundary-embedded architecture, outperforms state-of-the-art neural operators and strong baselines by an average of 60.96\%. Our source code can be found https://github.com/AI4Science-WestlakeU/beno.git.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Combining differentiable pde solvers and graph neural networks for fluid flow prediction. In international conference on machine learning, pp. 2402–2411. PMLR, 2020.
  2. Mesh generation and optimal triangulation. In Computing in Euclidean geometry, pp.  47–123. World Scientific, 1995.
  3. Message passing neural pde solvers. arXiv preprint arXiv:2202.03376, 2022.
  4. Francis F Chen. Introduction to Plasma Physics and Controlled Fusion (3rd Ed.). Springer, 2016.
  5. Finite difference methods, theory and applications. Springer, 2015.
  6. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks, 107:3–11, 2018.
  7. Pde-gcn: Novel architectures for graph neural networks motivated by partial differential equations. Advances in neural information processing systems, 34:3836–3849, 2021.
  8. Fast Graph Representation Learning with PyTorch Geometric, 2019.
  9. Physics-informed graph neural galerkin networks: A unified framework for solving pde-governed forward and inverse problems. Computer Methods in Applied Mechanics and Engineering, 390:114502, 2022.
  10. Neural message passing for quantum chemistry. In International conference on machine learning, pp. 1263–1272. PMLR, 2017.
  11. Adaptive fourier neural operators: Efficient token mixers for transformers. arXiv preprint arXiv:2111.13587, 2021.
  12. Multiwavelet-based operator learning for differential equations. Advances in neural information processing systems, 34:24048–24062, 2021.
  13. Non-linear operator approximations for initial value problems. In International Conference on Learning Representations (ICLR), 2022.
  14. Group equivariant fourier neural operators for partial differential equations. arXiv preprint arXiv:2306.05697, 2023.
  15. C. Hirsch. Numerical computation of internal and external flows: The fundamentals of computational fluid dynamics. Elsevier, 2007.
  16. K Ho-Le. Finite element mesh generation methods: a review and classification. Computer-aided design, 20(1):27–38, 1988.
  17. T. J. R. Hughes. The finite element method: linear static and dynamic finite element analysis. Courier Corporation, 2012.
  18. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  19. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  20. Two algorithms for constructing a delaunay triangulation. International Journal of Computer & Information Sciences, 9(3):219–242, 1980.
  21. Finite element operator network for solving parametric pdes. arXiv preprint arXiv:2308.04690, 2023.
  22. R. J. LeVeque. Finite difference methods for ordinary and partial differential equations: steady-state and time-dependent problems. SIAM, 2007.
  23. Fourier neural operator for parametric partial differential equations. arXiv preprint arXiv:2010.08895, 2020a.
  24. Neural operator: Graph kernel network for partial differential equations. arXiv preprint arXiv:2003.03485, 2020b.
  25. Multipole graph neural operator for parametric partial differential equations. Advances in Neural Information Processing Systems, 33:6755–6766, 2020c.
  26. Fourier neural operator with learned deformations for pdes on general geometries. arXiv preprint arXiv:2207.05209, 2022.
  27. Learning the dynamics of physical systems from sparse observations with finite element networks. arXiv preprint arXiv:2203.08852, 2022.
  28. Network in network. arXiv preprint arXiv:1312.4400, 2013.
  29. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983, 2016.
  30. Learning the solution operator of boundary value problems using graph neural networks. arXiv preprint arXiv:2206.14092, 2022.
  31. Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators. arXiv preprint arXiv:1910.03193, 2019.
  32. Care: Modeling interacting dynamics under temporal environmental variation. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  33. Fionn Murtagh. Multilayer perceptrons for classification and regression. Neurocomputing, 2(5-6):183–197, 1991.
  34. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché Buc, E. Fox, and R. Garnett (eds.), Advances in Neural Information Processing Systems 32, pp.  8024–8035. Curran Associates, Inc., 2019.
  35. Normalization: A preprocessing stage. arXiv preprint arXiv:1503.06462, 2015.
  36. Learning mesh-based simulation with graph networks. arXiv preprint arXiv:2010.03409, 2020.
  37. Numerical approximation of partial differential equations, volume 23. Springer Science & Business Media, 2008.
  38. Béatrice Rivière. Discontinuous Galerkin Methods for Solving Elliptic and Parabolic Equations. Society for Industrial and Applied Mathematics, 2008. doi: 10.1137/1.9780898717440. URL https://epubs.siam.org/doi/abs/10.1137/1.9780898717440.
  39. Y. Saad. Iterative methods for sparse linear systems. SIAM, 2003.
  40. Graph networks as learnable physics engines for inference and control. In International Conference on Machine Learning, pp. 4470–4479. PMLR, 2018.
  41. Learning to simulate complex physics with graph networks. In International conference on machine learning, pp. 8459–8468. PMLR, 2020.
  42. Green’s functions and boundary value problems. John Wiley & Sons, 2011.
  43. Factorized fourier neural operators. arXiv preprint arXiv:2111.13802, 2021.
  44. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  45. Coupled multiwavelet neural operator learning for coupled partial differential equations. arXiv preprint arXiv:2303.02304, 2023.
  46. Learning to solve pde-constrained inverse problems with graph networks. arXiv preprint arXiv:2206.00711, 2022.
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now