English
Related papers

Related papers: A Survey on Kolmogorov-Arnold Network

200 papers

Kolmogorov Arnold Networks (KANs) are neural architectures inspired by the Kolmogorov Arnold representation theorem that leverage B Spline parameterizations for flexible, locally adaptive function approximation. Although KANs can capture…

Machine Learning · Computer Science 2025-03-04 Wenhao Liang , Wei Emma Zhang , Lin Yue , Miao Xu , Olaf Maennel , Weitong Chen

AI for partial differential equations (PDEs) has garnered significant attention, particularly with the emergence of Physics-informed neural networks (PINNs). The recent advent of Kolmogorov-Arnold Network (KAN) indicates that there is…

Graph Representation Learning aims to create effective embeddings for nodes and edges that encapsulate their features and relationships. Graph Neural Networks (GNNs) leverage neural networks to model complex graph structures. Recently, the…

Machine Learning · Computer Science 2025-01-23 Muhieddine Shebaro , Jelena Tešić

Kolmogorov-Arnold networks (KANs) offer a potent combination of accuracy and interpretability, thanks to their compositions of learnable univariate activation functions. However, the activations of well-fitting KANs tend to exhibit…

Machine Learning · Computer Science 2026-05-05 James Bagrow

Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to traditional Multi-Layer Perceptrons (MLPs), offering enhanced interpretability and a solid mathematical foundation. However, their parameter efficiency remains a…

Machine Learning · Computer Science 2025-10-09 Di Zhang

The memory wall problem arises due to the disparity between fast processors and slower memory, causing significant delays in data access, even more so on edge devices. Data prefetching is a key strategy to address this, with traditional…

Hardware Architecture · Computer Science 2025-04-15 Dhruv Kulkarni , Bharat Bhammar , Henil Thaker , Pranav Dhobi , R. P. Gohil , Sai Manoj Pudukotai Dinkarrao

This short paper is a fast proof-of-concept that the 3-order B-splines used in Kolmogorov-Arnold Networks (KANs) can be well approximated by Gaussian radial basis functions. Doing so leads to FastKAN, a much faster implementation of KAN…

Machine Learning · Computer Science 2024-05-14 Ziyao Li

Reinforcement learning (RL) has been increasingly applied to network control problems, such as load balancing. However, existing RL approaches often suffer from lack of interpretability and difficulty in extracting controller equations. In…

Machine Learning · Computer Science 2025-05-21 Kamal Singh , Sami Marouani , Ahmad Al Sheikh , Pham Tran Anh Quang , Amaury Habrard

Function approximation using Haar basis systems offers an efficient implementation when compressed via Patricia trees while retaining the flexibility of wavelets for both global and local fitting. However, like B-spline-based…

Machine Learning · Computer Science 2026-02-05 Susumu Katayama

Neural networks are powerful parametric function approximators, while Gaussian processes (GPs) are nonparametric probabilistic models that place distributions over functions via kernel-defined correlations but become computationally…

Machine Learning · Computer Science 2025-12-09 Masoud Ataei , Vikas Dhiman , Mohammad Javad Khojasteh

Despite their immense success, deep convolutional neural networks (CNNs) can be difficult to optimize and costly to train due to hundreds of layers within the network depth. Conventional convolutional operations are fundamentally limited by…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Ray Congrui Yu , Sherry Wu , Jiang Gui

Recurrent Neural Networks (RNNs) have revolutionized many areas of machine learning, particularly in natural language and data sequence processing. Long Short-Term Memory (LSTM) has demonstrated its ability to capture long-term dependencies…

Machine Learning · Computer Science 2025-08-01 Remi Genet , Hugo Inzirillo

Kolmogorov-Arnold Networks (KANs) have gained attention for their potential to outperform Multi-Layer Perceptrons (MLPs) in terms of parameter efficiency and interpretability. Unlike traditional MLPs, KANs use learnable non-linear…

Hardware Architecture · Computer Science 2026-03-19 Sohaib Errabii , Olivier Sentieys , Marcello Traiola

Nuclear mass prediction is one of the core issues in nuclear physics research, yet it faces the challenge of small-sample datasets with high complexity. This study introduces the Kolmogorov-Arnold Network (KAN) into the refinement of…

Nuclear Theory · Physics 2026-03-17 Yanhua Lu , Tianshuai Shang , Pengxiang Du , Jian Li , Haozhao Liang

Kolmogorov-Arnold Networks (KANs) have recently shown promise for solving partial differential equations (PDEs). Yet their original formulation is computationally and memory intensive, motivating the introduction of Chebyshev Type-I-based…

Machine Learning · Computer Science 2026-01-19 Hangwei Zhang , Zhimu Huang , Yan Wang

Kolmogorov Arnold Networks (KANs) represent a new class of neural architectures that replace conventional linear transformations and node-based nonlinearities with spline-based function approximations distributed along network edges.…

Machine Learning · Computer Science 2026-01-30 Kazi Ahmed Asif Fuad , Lizhong Chen

Kolmogorov-Arnold Networks (KANs) are highly effective in long-term time series forecasting due to their ability to efficiently represent nonlinear relationships and exhibit local plasticity. However, prior research on KANs has…

Machine Learning · Computer Science 2025-06-17 Xiaoyan Kui , Canwei Liu , Qinsong Li , Zhipeng Hu , Yangyang Shi , Weixin Si , Beiji Zou

Kolmogorov-Arnold Networks (KANs) have gained attention as an alternative to traditional multilayer perceptrons (MLPs) for deep learning applications in computational physics, particularly for solving inverse problems with sparse data, as…

Machine Learning · Computer Science 2025-06-24 Ali Kashefi , Tapan Mukerji

In this paper, we present an innovative federated learning (FL) approach that utilizes Kolmogorov-Arnold Networks (KANs) for classification tasks. By utilizing the adaptive activation capabilities of KANs in a federated framework, we aim to…

Machine Learning · Computer Science 2024-11-12 Engin Zeydan , Cristian J. Vaca-Rubio , Luis Blanco , Roberto Pereira , Marius Caus , Abdullah Aydeger

Partial differential equations (PDEs) form a central component of scientific computing. Among recent advances in deep learning, evolutionary neural networks have been developed to successively capture the temporal dynamics of time-dependent…

Machine Learning · Computer Science 2026-02-24 Bongseok Kim , Jiahao Zhang , Guang Lin