paper-with-me

Papers

asKAN: Active Subspace embedded Kolmogorov-Arnold Network

2025-04-07 · Zhiteng Zhou, Zhaoyue Xu, Yi Liu, Shizhao Wang

The Kolmogorov-Arnold Network (KAN) has emerged as a promising neural network architecture for small-scale AI+Science applications. However, it suffers from inflexibility in modeling ridge functions, which is widely used in representing the relationships in physical systems. This study investigates this inflexibility through the lens of the Kolmogorov-Arnold theorem, which starts the representation of multivariate functions from constructing the univariate components rather than combining the independent variables. Our analysis reveals that incorporating linear combinations of independent variables can substantially simplify the network architecture in representing the ridge functions. Inspired by this finding, we propose active subspace embedded KAN (asKAN), a hierarchical framework that synergizes KAN's function representation with active subspace methodology. The architecture strategically embeds active subspace detection between KANs, where the active subspace method is used to identify the primary ridge directions and the independent variables are adaptively projected onto these critical dimensions. The proposed asKAN is implemented in an iterative way without increasing the number of neurons in the original KAN. The proposed method is validated through function fitting, solving the Poisson equation, and reconstructing sound field. Compared with KAN, asKAN significantly reduces the error using the same network architecture. The results suggest that asKAN enhances the capability of KAN in fitting and solving equations in the form of ridge functions.

📄 PDF Abstract BibTeX arXiv:2504.04669

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

+ ( 1 ) ⟷ 805 ⟷ ( 330 ) ⟷ 4056|How do I file a complaint with Expedia? How do I file a complaint with Expedia contact customer service at + ( 1 ) ⟷ 888 ⟷ ( 829 ) ⟷ 0881 or + ( 1 ) ⟷ 805 ⟷ ( 330 ) ⟷ 4056, or use their Help Center. Explain your issue…

Similar Papers 제목 키워드 기반

Scalable Bayesian Physics-Informed Kolmogorov-Arnold Networks

2025-01-15 · Zhiwei Gao, George Em Karniadakis

Uncertainty quantification (UQ) plays a pivotal role in scientific machine learning, especially when surrogate models are used to approximate complex systems. Although multilayer perceptions (MLPs) are commonly employed …

Kolmogorov-Arnold NetworksUncertainty Quantification

Learning the Basis: A Kolmogorov-Arnold Network Approach Embedding Green's Function Priors

2025-11-11 · Rui Zhu, Yuexing Peng, George C. Alexandropoulos, Wenbo Wang 외 arxiv

The Method of Moments (MoM) is constrained by the usage of static, geometry-defined basis functions, such as the Rao-Wilton-Glisson (RWG) basis. This letter reframes electromagnetic modeling around a learnable basis repr…

GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks

2024-06-19 · Fan Zhang, Xin Zhang

Massive number of applications involve data with underlying relationships embedded in non-Euclidean space. Graph neural networks (GNNs) are utilized to extract features by capturing the dependencies within graphs. Despit…

Kolmogorov-Arnold Networks

KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements

2024-10-22 · Md Meftahul Ferdaus, Mahdi Abdelguerfi, Elias Ioup, David Dobson 외

We introduce KANICE (Kolmogorov-Arnold Networks with Interactive Convolutional Elements), a novel neural architecture that combines Convolutional Neural Networks (CNNs) with Kolmogorov-Arnold Network (KAN) principles. KA…

Computational Efficiencyimage-classificationImage ClassificationKolmogorov-Arnold Networks

KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward

2024-11-15 · Divesh Basina, Joseph Raj Vishal, Aarya Choudhary, Bharatesh Chakravarthi

The curse of dimensionality poses a significant challenge to modern multilayer perceptron-based architectures, often causing performance stagnation and scalability issues. Addressing this limitation typically requires va…

Kolmogorov-Arnold Networks