Kolmogorov-Arnold Networks

Also known as KAN

Kolmogorov-Arnold Networks replace fixed scalar weights and activations with learnable one-dimensional functions on network edges, commonly represented by splines, radial basis functions, or polynomials. Researchers develop new bases and architectures, combine KANs with convolution, attention, or recurrent components, and use physics-informed and weak-form training for scientific problems such as partial differential equations. The functional structure can make learned relationships easier to inspect and supports applications in forecasting, vision, and scientific modeling, alongside theoretical work on approximation and generalization. A central tension is that expressive edge functions can be costly to evaluate, and theoretical universality does not guarantee better accuracy or efficiency than MLPs; performance depends on target structure, basis choice, and deployment hardware.

Latest papers

126 papers13 papers in the last four weeks, up 18% on the four weeks before. 0.1% of all new papers.

Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data
Nov 2, 2026Rafał Wodziński, Paweł SzczerbiakKolmogorov-Arnold Networks Tabular Classification
Sano Centre for Computational Medicine, Kraków, Poland · Department of Computer Science, Faculty of Computer Science and Mathematics, Cracow University of Technology, Kraków, Poland · Faculty of Computer Science, AGH University of Krakow, Kraków, Poland
Edge-Centric Adaptive Neural Activation via Parametric Tanh Functions
Oct 25, 2026Andreas FalkenbergNeural Network Activation Functions Kolmogorov-Arnold Networks
QPI Laboratories, Inc., USA
Tractable Inference with Kolmogorov-Arnold Networks
Oct 21, 2026Juan Diego Toscano, Sascha Ranftl, Zhiwei Gao +2Kolmogorov-Arnold Networks Neural Surrogate Modeling
Division of Applied Mathematics, Brown University, Providence, 02912, RI, USA · Division of Mathematical Sciences, Nanyang Technological University, 637371, Singapore
GeoDiv KAN Solver for Time Fractional Navier Stokes Equations on Complex Domains to Realistic CFD Reconstruction
Oct 19, 2026Yatin Kumar, Shivani Saini, Ramesh Kumar VatsNeural PDE Solvers Partial Differential Equations
Department of Mathematics and Scientific Computing, National Institute of Technology Hamirpur, Hamirpur, Himachal Pradesh, 177005, India
Out-of-Distribution Detection in Continual Learning
Oct 19, 2026Nimeshika Udayangani, Flora D. Salim, Christopher Leckie +1OOD Detection Continual Learning
School of Computing and Information Systems, The University of Melbourne, Australia · School of Computer Science Engineering, University of New South Wales, Australia
FHKAN: Fractional Hermite Kolmogorov-Arnold Networks for Data-Driven and Physics-Informed Learning
Oct 18, 2026Arsha Farnoush, Amirhossein Sadr, Aida Pakniyat +3Kolmogorov-Arnold Networks
Department of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran · School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran · School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield, UK +3
Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias
Oct 15, 2026Yunhao Ni, Yuxin Guo, Jie Luo +2Curse of Dimensionality Kolmogorov-Arnold Networks
State Key Laboratory of Complex and Critical Software Environment, Beihang University, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China
KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks
Oct 14, 2026Lukas Niehaus, Robin Rawiel, Ulf KrumnackKolmogorov-Arnold Networks Neural Network Interpretability
University Osnabrueck · University of Applied Sciences Osnabrueck
HankelKANet: Lightweight Path Loss Estimation via Physics-Inspired Hankel Convolution
Oct 14, 2026Yue Ruan, Xiaoxiao Cheng, Yunan Zhu +2Radio Propagation Modeling Physics-Informed ML
School of Computer Science and Technology, Anhui University of Technology, Maanshan 243002, China · Department of Electrical and Electronic Engineering, Imperial College London, SW7 2AZ London, U.K.
Hybrid Parallel Bessel KAN Model: a Kolmogorov Arnold Network: integrated framework for developing a novel architecture to reconstruct the fused-basis approach via a parameter free quadratic interaction
Oct 13, 2026Mintu Pathak, Meshv Patel, Mohendra Roy +1Kolmogorov-Arnold Networks Modular Neural Networks
Department of Applied Sciences, Tezpur University, Napaam, Tezpur, 784028, Assam, India. · Department of ICT, Pandit Deendayal Energy University, Raysan, Gandhinagar, 382007, Gujarat, India.
Low-Rank Kolmogorov-Arnold Generator Flows for Interpretable Operator Learning
Oct 9, 2026Minjong CheonOperator Learning PDE Operator Learning
Department of Computer Science, Korea National Open University, Seoul, South Korea.
Robust Prediction of Internal Wave-Affected Multi-Scale Sound Speed Distribution Using Lightweight Kolmogorov-Arnold Networks with Hybrid Basis Functions
Oct 7, 2026Wei Huang, Junpeng Lu, Tianhe Xu +2Underwater Acoustics Kolmogorov-Arnold Networks
Faculty of Information Science and Engineering, Ocean University of China, Qingdao, Shandong 266404, China · School of Space Science and Technology, Shandong University at Weihai, Weihai, Shandong 264200, China · School of Artificial Intelligence, The Chinese University of Hong Kong (Shenzhen), Shenzhen, Guangdong 518172, China
Sample-Efficiency of Kolmogorov-Arnold Networks
Oct 7, 2026Kevin Riehl, Shaimaa K. El-Baklish, Fan Wu +1Kolmogorov-Arnold Networks Sample-Efficient RL
ETH Zürich, IVT & Agentic Systems Lab (ASL) · ETH Zürich, IVT · ETH Zürich, Agentic Systems Lab (ASL)
IGA-KAN: Isogeometric Analysis with Physics-Informed Closed-Form Kolmogorov-Arnold Networks for Forward and Inverse PDEs
Oct 5, 2026Sima Naraghi, Kourosh Parand, Amirhossein Sadr +1Neural PDE Solvers Kolmogorov-Arnold Networks
Department of Applied Mathematics, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran · Department of Computer and Data Sciences, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran · Department of Cognitive Modeling, Institute for Cognitive and Brain Sciences, Shahid Beheshti University, Tehran, Iran +1
Kolmogorov-Arnold Networks for Personal Context Recognition on ExtraSensory
Oct 4, 2026Hoang-Thang TaKolmogorov-Arnold Networks
University of Information Technology, Ho Chi Minh City, Vietnam · Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam
Kolmogorov-Arnold Networks for Free-Boundary Partial Differential Equations
Oct 1, 2026Tan Phuong Dong LeNeural PDE Solvers PDE Solving
Department of Applied Mathematics, University of Waterloo, Canada · Department of Statistics and Actuarial Science, University of Waterloo, Canada
Neural scaling laws and evolution of learnable activation functions of Kolmogorov-Arnold networks
Oct 1, 2026Tilen Cadez, Sanghoon Lee, Kyoung-Min KimNeural Network Activation Functions Kolmogorov-Arnold Networks
Asia Pacific Center for Theoretical Physics, Pohang, Gyeongbuk, 37673, Republic of Korea · Department of Physics, Pohang University of Science and Technology, Pohang, Gyeongbuk 37673, Republic of Korea
Hardware-Aware Functional Kolmogorov-Arnold Networks for Efficient Medical Image Enhancement and Segmentation
Sep 28, 2026Mohammad Sadegh SirjaniEfficient Neural Network Inference Kolmogorov-Arnold Networks
Department of Computer Science University of Texas at San Antonio, San Antonio, TX, USA
Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons
Sep 26, 2026Ami Tavory, Meir FederNeural Network Interpretability Kolmogorov-Arnold Networks
Meta Platforms Tel-Aviv, Israel · School of Electrical and Computer Engineering Tel-Aviv University Tel-Aviv, Israel
Evaluating the Effectiveness of SechKAN on 1D Data
Sep 22, 2026Hoang-Thang TaTime Series Classification Kolmogorov-Arnold Networks
University of Information Technology, Ho Chi Minh City, Vietnam · Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam
Rethinking Vision Architectures with Gated Linear Attention and KAN
Sep 18, 2026Ali Mehizel, Oussama KhaldiVisual Representation Learning Vision Transformer
Department of Applied Statistics, ENSSEA, Kolea, Tipaza, Algeria
Stability-Constrained Approximation in Spline KANs: Exact Layer Balancing and Budget-Compatible Saturation
Sep 14, 2026Aleksander TankmanFunction Approximation Neural Network Approximation Theory
Fivestar Europe OÜ, Tallinn, Estonia
Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks
Sep 14, 2026Masoud Ataei, Mohammad Javad Khojasteh, Vikas DhimanUncertainty Quantification Kolmogorov-Arnold Networks
Electrical and Computer Engg. University of Maine Orono, ME, USA · Electrical and Microelectronic Engg. Rochester Institute of Technology Rochester, NY, USA
Scalability Analysis of Distributed Kolmogorov-Arnold Network Training on High-Performance Computing Systems
Sep 7, 2026Guangneng Chen, David Garcia Selfa, Pablo Quesada BarriusoHigh-Performance Computing Kolmogorov-Arnold Networks
University of Santiago de Compostela, 15782 Santiago de Compostela, Spain · Galicia Supercomputing Center (CESGA), 15705 Santiago de Compostela, Spain
Kolmogorov--Arnold stability for discontinuous functions
Sep 7, 2026Sviatoslav V. DzhenzherAdversarial Robustness Kolmogorov-Arnold Networks
Moscow Institute of Physics and Technology 141701, Institutskii lane, 9, Dolgoprudny, Russia.
KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models
Sep 4, 2026Phuong Tuan Dat, Phuong Khai Minh, Tran Huy DatAdapter Tuning Parameter-Efficient Fine-Tuning
Dept. of Electrical and Computer Engineering, National University of Singapore · School of Computing, National University of Singapore · Institute of Advanced Intelligence and Computing (IAIC), A∗STAR
SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials
Sep 3, 2026Amirhosein Azarpour, Seyyed Moein KazemiFunction Approximation Kolmogorov-Arnold Networks
Faculty of Mathematical Sciences, Department of Computer Science, Shahid Beheshti University, Tehran · Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran
InKAN: B-Spline KANs via Truncated Power Form
Sep 2, 2026Naveen MysoreEfficient Neural Network Inference Neural Network Activation Functions
RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis
Sep 1, 2026Amirhosein AzarpourPolynomial Neural Networks Kolmogorov-Arnold Networks
Department of Computer Science Shahid Beheshti University Tehran, Iran
Kolmogorov--Arnold against bounded translations
Aug 31, 2026Sviatoslav V. DzhenzherAdversarial Robustness Kolmogorov-Arnold Networks
Moscow Institute of Physics and Technology 141701, Institutskii lane, 9, Dolgoprudny, Russia.

Nov 2, 2026J/K move · Enter open · S save

Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data

Rafał Wodziński, Paweł Szczerbiak

Sano Centre for Computational Medicine, Kraków, Poland · Department of Computer Science, Faculty of Computer Science and Mathematics, Cracow University of Technology, Kraków, Poland · Faculty of Computer Science, AGH University of Krakow, Kraków, Poland

Kolmogorov-Arnold Networks Tabular Classification Tabular ML Multilayer Perceptrons

Open paper AskPDF arXiv

Kolmogorov-Arnold Networks (KANs) have recently been proposed as a promising alternative to Multi-Layer Perceptrons (MLPs). However, empirical evaluations on structured medical datasets remain scarce, and commonly reported metrics like AUROC can yield overly optimistic performance estimates on imbalanced clinical cohorts. In this study, we present a standardized benchmark comparing eleven architectures - nine KAN variants (FastKAN, WavKAN, ReLUKAN, ChebyKAN, TaylorKAN, GramKAN, JacobiKAN, LegendreKAN, and TabKAN), a tuned StandardMLP, and a Random Forest baseline - across seven heterogeneous medical tabular datasets spanning oncology, cardiology, nephrology, neurology, endocrinology, and obstetrics. Our experimental protocol employs a 3x5 Repeated Stratified K-Fold cross-validation scheme with nested Bayesian hyperparameter optimization and evaluates discrimination via Area Under the Precision-Recall Curve (AUPRC), calibration through the Brier Score, and computational efficiency. Formal equivalence testing is conducted using the Bayesian Correlated t-Test with a Region of Practical Equivalence (ROPE) at +/- 0.01. The results indicate that on datasets with severe class imbalance, dedicated KAN architectures (particularly TabKAN and ReLUKAN) can improve minority-class detection and achieve higher AUPRC than standard MLPs. Nevertheless, across pooled datasets, KAN variants demonstrate comparable overall predictive discrimination rather than a systematic advantage, while requiring 1.20x to 1.48x longer inference latency per sample and up to 12.5x more trainable parameters. Consequently, StandardMLP remains a strong baseline on the efficiency Pareto frontier, while KAN variants provide a viable alternative when precision on rare positive cases is the primary clinical objective. The code for reproducing the results is available at https://github.com/rafalwodzinski/kan_mlp_comparison.