Data to 7 Oct 2026

Convolutional Kolmogorov-Arnold Networks

arXiv 2406.13155 ↗First posted 19 Jun 2024cs.CV cs.AIcited by 76

Not on the map. Why?

Abstract (arXiv)

In this paper, we present Convolutional Kolmogorov-Arnold Networks, a novel architecture that integrates the learnable spline-based activation functions of Kolmogorov-Arnold Networks (KANs) into convolutional layers. By replacing traditional fixed-weight kernels with learnable non-linear functions, Convolutional KANs offer a significant improvement in parameter efficiency and expressive power over standard Convolutional Neural Networks (CNNs). We empirically evaluate Convolutional KANs on the Fashion-MNIST dataset, demonstrating competitive accuracy with up to 50% fewer parameters compared to baseline classic convolutions. This suggests that the KAN Convolution can effectively capture complex spatial relationships with fewer resources, offering a promising alternative for parameter-efficient deep learning models.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Builds on 3 of its 9 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

3 of 9 references.

References · 3

2013Predicting Parameters in Deep Learningcited by 223
2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 160
2024Kolmogorov-Arnold Networks are Radial Basis Function Networkscited by 125

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 33; 2025: 29; 2026: 14.

76 papers.

Sort:

By area:

2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 116
2024A Survey on Kolmogorov-Arnold Networkcited by 67
2024Kolmogorov-Arnold Transformercited by 56
2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 48
2024On the expressiveness and spectral bias of KANscited by 36
2024Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problemscited by 35
2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecastingcited by 27
2024Exploring the Limitations of Kolmogorov-Arnold Networks in Classification: Insights to Software Training and Hardware Implementationcited by 22
2024Reduced Effectiveness of Kolmogorov-Arnold Networks on Functions with Noisecited by 17
2024PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Setscited by 15
2024DropKAN: Regularizing KANs by masking post-activationscited by 14
2024F-KANs: Federated Kolmogorov-Arnold Networkscited by 14

38 more

2025KANEL'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluationcited by 13
2025LeanKAN: A Parameter-Lean Kolmogorov-Arnold Network Layer with Improved Memory Efficiency and Convergence Behaviorcited by 12
2024Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networkscited by 11
2026Evolving Medical Imaging Agents via Experience-driven Self-skill Discoverycited by 10
2024Multifidelity Kolmogorov-Arnold Networkscited by 9
2024Bayesian Kolmogorov Arnold Networks (Bayesian_KANs): A Probabilistic Approach to Enhance Accuracy and Interpretabilitycited by 8
2024Kolmogorov-Arnold Network Autoencoderscited by 8
2025MedKAN: An Advanced Kolmogorov-Arnold Network for Medical Image Classificationcited by 8
2024KAN versus MLP on Irregular or Noisy Functionscited by 7
2024A preliminary study on continual learning in computer vision using Kolmogorov-Arnold Networkscited by 7
2024TransUKAN:Computing-Efficient Hybrid KAN-Transformer for Enhanced Medical Image Segmentationcited by 6
2025Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stabilitycited by 6
2024HyperKAN: Kolmogorov-Arnold Networks make Hyperspectral Image Classificators Smartercited by 5
2024Rethinking the Function of Neurons in KANscited by 5
2024HaSPeR: An Image Repository for Hand Shadow Puppet Recognitioncited by 5
2024LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Modelcited by 5
2024GaRField++: Reinforced Gaussian Radiance Fields for Large-Scale 3D Scene Reconstructioncited by 5
2024Residual Kolmogorov-Arnold Network for Enhanced Deep Learningcited by 5
2025CVKAN: Complex-Valued Kolmogorov-Arnold Networkscited by 5
2025Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learningcited by 5
2025RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritiscited by 5
2024Incorporating Arbitrary Matrix Group Equivariance into KANscited by 4
2025Exploring Adversarial Transferability between Kolmogorov-arnold Networkscited by 4
2024KAN v.s. MLP for Offline Reinforcement Learningcited by 3
2024KANs for Computer Vision: An Experimental Studycited by 3
2025AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learningcited by 3
2025Physics-informed KAN PointNet: Deep learning for simultaneous solutions to inverse problems in incompressible flow on numerous irregular geometriescited by 3
2025KAN or MLP? Point Cloud Shows the Way Forwardcited by 3
2025Improving Memory Efficiency for Training KANs via Meta Learningcited by 3
2025Interpretable Clinical Classification with Kolmogorov-Arnold Networkscited by 3
2025KAN-SAs: Efficient Acceleration of Kolmogorov-Arnold Networks on Systolic Arrayscited by 3
2024Kolmogorov Arnold Networks in Fraud Detection: Bridging the Gap Between Theory and Practicecited by 2
2024P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimizationcited by 2
2025Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?cited by 2
2025KANITE: Kolmogorov-Arnold Networks for ITE estimationcited by 2
2025On the Rate of Convergence of Kolmogorov-Arnold Network Regression Estimatorscited by 2
2025CausalKANs: interpretable treatment effect estimation with Kolmogorov-Arnold networkscited by 2
2025MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Networkcited by 2

50 most cited of 76 All 76 (JSON)