Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs

• URL: http://arxiv.org/abs/2606.24371v1
• Date: Tue, 23 Jun 2026 10:00:26 GMT
• Title: Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs
• Abstract summary: Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions.<n>We argue that the learnable functions are better placed in the emphstructure of the convolution than on each edge.
• Score: 76.06235645266621
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and prone to overfitting. We argue that the learnable functions are better placed in the \emph{structure} of the convolution than on each edge, and we organise the design space along a single axis: whether the function acts on the pixel \emph{values} or on the filter \emph{shape}. We study three realisations. SV-KAN applies one shared univariate function to the values and leaves the spatial filter free and static, aa classical convolution with a single learnable shared activation. AG-KAN keeps the shared value function but supplies the spatial structure through a content-adaptive Gaussian gate. RF-KAN instead moves the learnable functions onto the filter shape, building each filter from oriented ridge profiles expanded in a localised oscillatory (Morlet) wavelet basis with content-adaptive amplitudes. Under a matched four-layer protocol with in-run references and three seeds, RF-KAN and SV-KAN reach $88.47\pm0.10\%$ and $88.20\pm0.31\%$ on CIFAR-10 and $64.40\pm0.19\%$ and $64.57\pm0.30\%$ on CIFAR-100, at about $0.4$M parameters. At this matched scale the shape model and the simplest value model meet at the top, both above a plain convolution and every per-edge KAN we tested, including the official Gram variant, at roughly a fifth of the parameters. A controlled study attributes the RF-KAN gain to an intrinsically localised oscillatory basis and to content adaptivity, and an ablation that removes the learned shape entirely, leaving only the shared value function, collapses accuracy by over forty points, identifying the learned shape as the load-bearing ingredient at this scale.

Related papers

• SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits [6.860988566886594]
  We present textbfSparseKAN, a unified approach that compresses KANs along three complementary axes: basis functions, neurons/channels, and numerical precision.<n>SparseKAN equips the base branch, nonlinear basis branch, and individual basis terms with hierarchical learnable gates trained under a differentiable active-cost objective.
  arXiv  Detail & Related papers  (2026-08-01T20:42:41Z)
• Multi-Modal Spatio-Temporal Graph Neural Network with Mixture of Experts for Soil Organic Carbon Prediction [0.0]
  Existing approaches face two limitations: they pair hand-crafted co-modals with classical ML or single-modal deep models that miss rich spectral and temporal information.<n>We introduce SpTG-NN, a multi-temporal graph neural network addressing both SpTGNN and grid-based architectures.<n>A fine-tuned TerraMind encoder extracts node features from Sentinel-2, Sentinel-1 and DEM signals.
  arXiv  Detail & Related papers  (2026-06-15T11:25:38Z)
• FI-KAN: Fractal Interpolation Kolmogorov-Arnold Networks [0.0]
  Kolmogorov-Arnold Networks (KAN) employ B-spline bases on a fixed grid, providing no intrinsic multi-scale decomposition for non-smooth function approximation.<n>We introduce Fractal Interpolation KAN (FI-KAN), which incorporates learnable fractal function (FIF) bases from iterated function system (IFS) theory into KAN.<n>Two variants are presented: Pure FI-KAN replaces B-splines entirely with FIF bases; Hybrid FI-KAN retains the B-spline path and adds a learnable fractal correction.
  arXiv  Detail & Related papers  (2026-03-30T11:09:07Z)
• Lookup multivariate Kolmogorov-Arnold Networks [5.639419519849473]
  High-dimensional linear mappings dominate both the parameter count and the computational cost of most modern deep-learning models.<n>We introduce a general-purpose drop-in replacement, lookup multivariate Kolmogorov-Arnold Networks (lmKANs)<n>lmKANs deliver a substantially better trade-off between capacity and inference cost.
  arXiv  Detail & Related papers  (2025-09-08T18:00:35Z)
• RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations [8.346566205092433]
  RecConv is a decomposition strategy that efficiently constructs multi-frequency representations using small- Kernel convolutions.<n> RecNeXt-M3 outperforms RepViT-M1.1 by 1.9 $APbox$ on COCO with similar FLOPs.
  arXiv  Detail & Related papers  (2024-12-27T13:13:52Z)
• Highly Adaptive Ridge [84.38107748875144]
  We propose a regression method that achieves a $n-2/3$ dimension-free L2 convergence rate in the class of right-continuous functions with square-integrable sectional derivatives. Har is exactly kernel ridge regression with a specific data-adaptive kernel based on a saturated zero-order tensor-product spline basis expansion. We demonstrate empirical performance better than state-of-the-art algorithms for small datasets in particular.
  arXiv  Detail & Related papers  (2024-10-03T17:06:06Z)
• Adaptive Split-Fusion Transformer [90.04885335911729]
  We propose an Adaptive Split-Fusion Transformer (ASF-former) to treat convolutional and attention branches differently with adaptive weights. Experiments on standard benchmarks, such as ImageNet-1K, show that our ASF-former outperforms its CNN, transformer counterparts, and hybrid pilots in terms of accuracy.
  arXiv  Detail & Related papers  (2022-04-26T10:00:28Z)
• Submodular + Concave [53.208470310734825]
  It has been well established that first order optimization methods can converge to the maximal objective value of concave functions. In this work, we initiate the determinant of the smooth functions convex body $$F(x) = G(x) +C(x)$. This class of functions is an extension of both concave and continuous DR-submodular functions for which no guarantee is known.
  arXiv  Detail & Related papers  (2021-06-09T01:59:55Z)
• PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer [76.44375136492827]
  Convolutional Neural Networks (CNNs) are often scale-sensitive. We bridge this regret by exploiting multi-scale features in a finer granularity. The proposed convolution operation, named Poly-Scale Convolution (PSConv), mixes up a spectrum of dilation rates.
  arXiv  Detail & Related papers  (2020-07-13T05:14:11Z)
• Region adaptive graph fourier transform for 3d point clouds [51.193111325231165]
  We introduce the Region Adaptive Graph Fourier Transform (RA-GFT) for compression of 3D point cloud attributes. The RA-GFT achieves better complexity-performance trade-offs than previous approaches.
  arXiv  Detail & Related papers  (2020-03-04T02:47:44Z)

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.