AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks

• URL: http://arxiv.org/abs/2606.01283v1
• Date: Sun, 31 May 2026 15:07:20 GMT
• Title: AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks
• Abstract summary: We propose a simple yet effective approach that learns adaptive kernel parameters within the neural network.<n>AdaKernel consistently improves various Graph Neural Networks (GNNs) and outperforms model-agnostic adaptive baselines.
• Score: 41.813456621843464
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modeling spatial dependencies is central to spatiotemporal data analysis using Graph Neural Networks (GNNs). Traditional methods rely on distance-based kernels with predefined parameters, which restricts model capacity. Although generic adaptive mechanisms (e.g., Graph Attention Networks) offer flexibility, they often fail to capture the underlying geometric structure, performing worse than distance-based models in data-sparse scenarios. Addressing this, we revisit the kernel parameterization problem and theoretically prove that misspecified kernel parameters introduce unavoidable approximation errors in GNNs. To overcome this, we propose AdaKernel, a simple yet effective approach that learns adaptive kernel parameters within the neural network. Unlike methods that learn graph structures from scratch, AdaKernel adopts a structure-preserving strategy that optimizes the scale of physical interactions rather than discarding them. Extensive experiments on Kriging, Imputation, and Forecasting demonstrate that AdaKernel consistently improves various GNN architectures and outperforms model-agnostic adaptive baselines, validating that accurately learned kernel parameters are superior to both fixed priors and fully latent graph structures.

Related papers

• Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel [67.14508461124932]
  Full-waveform inversion (FWI) estimates unknown parameters in the wave equation from limited boundary measurements.<n>Recent advances in neural reparameterized FWI (NeurFWI) demonstrate that representing the parameters using a neural network can reduce the reliance on the high-quality initial model and wavefield data.<n>In this study, we establish the neural sensitivity kernel (NSK) and the wave tangent kernel (WTK) to analyze their convergence behavior from both model and data domains.
  arXiv  Detail & Related papers  (2026-05-14T04:49:23Z)
• A Framework for Nonstationary Gaussian Processes with Neural Network Parameters [0.8057006406834466]
  We propose a framework that uses nonstationary kernels whose parameters vary across the feature space, modeling these parameters as the output of a neural network.<n>Our method clearly describes the behavior of the nonstationary parameters and is compatible with approximation methods for scaling to large datasets.<n>We test a nonstationary variance and noise variant of our method on several machine learning datasets and find that it achieves better accuracy and log-score than both a stationary model and a hierarchical model approximated with variational inference.
  arXiv  Detail & Related papers  (2025-07-16T14:09:49Z)
• Scalable Gaussian Processes with Low-Rank Deep Kernel Decomposition [7.532273334759435]
  Kernels are key to encoding prior beliefs and data structures in Gaussian process (GP) models.<n>Deep kernel learning enhances kernel flexibility by feeding inputs through a neural network before applying a standard parametric form.<n>We introduce a fully data-driven, scalable deep kernel representation where a neural network directly represents a low-rank kernel.
  arXiv  Detail & Related papers  (2025-05-24T05:42:11Z)
• Identification of vortex in unstructured mesh with graph neural networks [0.0]
  We present a Graph Neural Network (GNN) based model with U-Net architecture to identify the vortex in CFD results on unstructured meshes. A vortex auto-labeling method is proposed to label vortex regions in 2D CFD meshes.
  arXiv  Detail & Related papers  (2023-11-11T12:10:16Z)
• Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagation [80.227864832092]
  Graph neural networks (GNNs) have exhibited exceptional efficacy in a diverse array of applications. The sheer size of large-scale graphs presents a significant challenge to real-time inference with GNNs. We propose an online propagation framework and two novel node-adaptive propagation methods.
  arXiv  Detail & Related papers  (2023-10-17T05:03:00Z)
• Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Kolmogorov n-width Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel [0.0]
  Reduced order models (ROMs) are widely used in scientific computing to tackle high-dimensional systems.<n>We propose a novel ROM framework that integrates optimal transport theory and neural network-based methods.<n>Our framework outperforms traditional ROM methods in terms of accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2023-08-26T10:24:43Z)
• Adaptive Kernel Graph Neural Network [21.863238974404474]
  Graph neural networks (GNNs) have demonstrated great success in representation learning for graph-structured data. In this paper, we propose a novel framework - i.e., namely Adaptive Kernel Graph Neural Network (AKGNN) AKGNN learns to adapt to the optimal graph kernel in a unified manner at the first attempt. Experiments are conducted on acknowledged benchmark datasets and promising results demonstrate the outstanding performance of our proposed AKGNN.
  arXiv  Detail & Related papers  (2021-12-08T20:23:58Z)
• Random Features for the Neural Tangent Kernel [57.132634274795066]
  We propose an efficient feature map construction of the Neural Tangent Kernel (NTK) of fully-connected ReLU network. We show that dimension of the resulting features is much smaller than other baseline feature map constructions to achieve comparable error bounds both in theory and practice.
  arXiv  Detail & Related papers  (2021-04-03T09:08:12Z)
• Flow-based Kernel Prior with Application to Blind Super-Resolution [143.21527713002354]
  Kernel estimation is generally one of the key problems for blind image super-resolution (SR) This paper proposes a normalizing flow-based kernel prior (FKP) for kernel modeling. Experiments on synthetic and real-world images demonstrate that the proposed FKP can significantly improve the kernel estimation accuracy.
  arXiv  Detail & Related papers  (2021-03-29T22:37:06Z)
• Finite Versus Infinite Neural Networks: an Empirical Study [69.07049353209463]
  kernel methods outperform fully-connected finite-width networks. Centered and ensembled finite networks have reduced posterior variance. Weight decay and the use of a large learning rate break the correspondence between finite and infinite networks.
  arXiv  Detail & Related papers  (2020-07-31T01:57:47Z)

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.