PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEs

• URL: http://arxiv.org/abs/2607.20378v1
• Date: Wed, 22 Jul 2026 17:08:29 GMT
• Title: PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEs
• Abstract summary: Physics-informed learning of partial differential equations (PDEs) has been dominated by multilayer perceptrons (MLPs)<n> Kolmogorov Arnold Networks (KANs) mitigate these limitations because their learnable activations are structurally aligned with the classical discretizations.<n>We present PG-KINN, a physics-informed KAN built on a Petrov-Galerkin formulation in which the test space is an independent, compactly supported, piecewise-polynomial space evaluated with Gauss-re quadrature.
• Score: 0.33585724475660284
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Physics-informed learning of partial differential equations (PDEs) has been dominated by multilayer perceptrons (MLPs), whose spectral bias and dense parameterization limit both accuracy and interpretability. Kolmogorov Arnold Networks (KANs) mitigate these limitations because their learnable spline activations are structurally aligned with the piecewise-polynomial bases of classical discretizations. However, the way a PDE is cast into a loss functional is as decisive as the choice of approximator: strong-form residual minimization requires high-order derivatives and heavily weighted losses, the energy (Bubnov-Galerkin) form is restricted to self-adjoint operators and, as we show, collapses to a trivial solution for parameter-identification problems, and boundary integral forms require a known fundamental solution. We propose PG-KINN, a physics-informed KAN built on a Petrov-Galerkin formulation in which the trial space is a KAN and the test space is an independent, compactly supported, piecewise-polynomial space evaluated with Gauss-Legendre quadrature. Integration by parts lowers the differentiation order while retaining applicability to general non-self-adjoint, nonlinear, and inverse problems; the localized test functions turn the global residual into a set of element-wise weak residuals with favorable conditioning. On a suite of benchmarks spanning crack singularities, stress concentration, Neo-Hookean hyperelasticity, inverse parameter identification in heterogeneous media, and complex geometries, PG-KINN consistently outperforms legacy MLP baselines and state-of-the-art KAN-based strong/energy/inverse formulations (PIKAN). These results position the Petrov-Galerkin coupling of KAN trial spaces and polynomial test spaces as a robust and accurate route for AI-based computational mechanics.

Related papers

• Characterizing Heterogeneous Rates in Finite Mixture Estimation via Partial Optimal Transport [88.55403215843967]
  Voronoi-based partial optimal transport (VPOT) for obtaining refined local and global convergence guarantees for the maximum likelihood estimator of the mixing measure.<n>Results hold in arbitrary fixed dimension without requiring mixing proportions to be uniformly bounded away from zero or prior knowledge of the true number of mixture components.
  arXiv  Detail & Related papers  (2026-09-15T04:32:53Z)
• Solution-space heterogeneity shapes federated learning dynamics across partial differential equations [41.890949680958805]
  Federated machine learning enables institutions to train neural surrogates without centralizing local physical data.<n>Existing protocols partition coordinates, coefficients, boundary conditions, or geometries according to equation-specific rules.<n>Here, we introduce solution-space PDE-Dirichlet, a protocol that converts continuous supervised responses into reusable solution bins.
  arXiv  Detail & Related papers  (2026-09-04T11:23:29Z)
• Interpretable Activation-Selection Neural Networks for Symbolic Regression of Parameter-Dependent Hamiltonian Eigenvalues [45.88028371034407]
  We introduce an activation-selection network (ASN), a differentiable symbolic-regression architecture.<n>Each input node learns a sparse combination of predefined analytical functions, and the trained network can be converted directly into an explicit expression.<n>We apply the ASN to effective three- and four-site spin-chain Hamiltonians relevant to zero-quantum nuclear magnetic resonance.
  arXiv  Detail & Related papers  (2026-08-26T07:45:10Z)
• Error-Conditioned Neural Solvers [36.51479208528461]
  Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical task.<n>Recent hybrid methods promote physical correctness by targeting the PDE residual via gradient descent or Gauss-Newton steps, but inherit the compute cost and instability of the underlying classical gradients.<n>We show, theoretically and empirically, that numerically minimizing the PDE residual can be an unreliable proxy for reconstruction accuracy in ill-conditioned systems.
  arXiv  Detail & Related papers  (2026-06-25T17:56:27Z)
• Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems [48.470700002941136]
  Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based optimization.<n> physics-informed neural networks (PINNs) have emerged as a flexible alternative.<n>We present a fair comparison of adjoint optimization and PINNs for PDE-constrained inverse problems.
  arXiv  Detail & Related papers  (2026-06-10T17:07:09Z)
• Stability and Bifurcation Analysis of Nonlinear PDEs via Random Projection-based PINNs: A Krylov-Arnoldi Approach [1.4174475093445233]
  We address the stability and bifurcation analysis of nonlinear partial differential equations (PDEs) in which the solution is sought in the function space spanned by physics-informed random projection neural networks (PI-RPNNs)<n>We introduce a matrix-free shift-invert Krylov-Arnoldi method that operates directly in weight space, avoiding explicit inversion of the numerically rank-deficient collocation matrix.<n>We prove that the PI-RPNN-based generalized eigenvalue problem is almost surely regular, guaranteeing solvability with standard eigensolvers.
  arXiv  Detail & Related papers  (2026-03-23T04:41:10Z)
• Physics-Informed Chebyshev Polynomial Neural Operator for Parametric Partial Differential Equations [17.758049557300826]
  We introduce the Physics-Informed Chebyshev Polynomial Neural Operator (CPNO)<n>CPNO replaces unstable monomial expansions with numerically stable Chebyshev spectral basis.<n> Experiments on benchmark parameterized PDEs show that CPNO achieves superior accuracy, faster convergence, and enhanced robustness to hyper parameters.
  arXiv  Detail & Related papers  (2026-02-02T07:19:56Z)
• 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)
• A Variational Physics-Informed Neural Network Framework Using Petrov-Galerkin Method for Solving Singularly Perturbed Boundary Value Problems [14.126509388112302]
  This work proposes a framework that integrates the Petrov-Galerkin formulation with deep neural networks (DNNs)<n>It solves one-dimensional singularly perturbed boundary value problems (BVPs) and parabolic partial differential equations (PDEs) involving one or two small parameters.
  arXiv  Detail & Related papers  (2025-09-13T18:25:00Z)
• Scalable unsupervised alignment of general metric and non-metric structures [21.29255788365408]
  Aligning data from different domains is a fundamental problem in machine learning with broad applications across very different areas. We learn a related well-scalable linear assignment problem (LAP) whose solution is also a minimizer of the quadratic assignment problem (QAP) We evaluate our approach on synthetic and real datasets from single-cell multiomics and neural latent spaces.
  arXiv  Detail & Related papers  (2024-06-19T12:54:03Z)
• On the Identification and Optimization of Nonsmooth Superposition Operators in Semilinear Elliptic PDEs [3.045851438458641]
  We study an infinite-dimensional optimization problem that aims to identify the Nemytskii operator in the nonlinear part of a prototypical semilinear elliptic partial differential equation (PDE) In contrast to previous works, we consider this identification problem in a low-regularity regime in which the function inducing the Nemytskii operator is a-priori only known to be an element of $H leakyloc(mathbbR)$.
  arXiv  Detail & Related papers  (2023-06-08T13:33:20Z)
• Efficient Error Certification for Physics-Informed Neural Networks [25.712851771991218]
  We introduce $partial$-CROWN: a general, efficient and scalable post-training framework to bound PINN residual errors. We demonstrate its effectiveness in obtaining certificates tight by applying it to two classically studied PINNs and two more challenging ones with real-world applications.
  arXiv  Detail & Related papers  (2023-05-17T12:19:43Z)
• DiffNet: Neural Field Solutions of Parametric Partial Differential Equations [30.80582606420882]
  We consider a mesh-based approach for training a neural network to produce field predictions of solutions to PDEs. We use a weighted Galerkin loss function based on the Finite Element Method (FEM) on a parametric elliptic PDE. We prove theoretically, and illustrate with experiments, convergence results analogous to mesh convergence analysis deployed in finite element solutions to PDEs.
  arXiv  Detail & Related papers  (2021-10-04T17:59:18Z)

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.