Work

Research Directions on Kolmogorov–Arnold Networks: A Comprehensive Review

Year: 2025

Type: article

Abstract: Utilizing the Kolmogorov–Arnold representation theorem, KANs have emerged as a mathematically rigorous and easily interpretable alternative to traditional neural networks. These networks decompose high-dimensional functions into sums of univariate continuous functions using adaptive activation functions. Compared to MLPs, KANs exhibit superior or comparable performance in accuracy, parameter efficiency, and interpretability. Applications highlight the advantages of KANs in solving complex partial differential equations with enhanced convergence and uncertainty quantification, modeling dynamic systems in a meaningful manner, and making reliable forecasts in the areas of power systems, environmental monitoring, and demand prediction. Based on current research on KANs, they demonstrate a promising frontier in interpretable deep learning, with increasing influence across numerous interdisciplinary scientific and engineering fields.

Source: Symmetry

DOI: 10.3390/sym18010060

Authors: Zhen Wang, Xiaomin Lin, Dayong Wang, Cui Cui, Xue Hao

Institutions: Guangdong University of Science and Technology, University of Technology Malaysia, Wenzhou University of Technology, Shandong College of Economics and Business

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funder: Guangdong University of Science and Technology