paper-with-me

홈 › Papers

MLPs and KANs for data-driven learning in physical problems: A performance comparison

2025-04-15 · Raghav Pant, Sikan Li, Xingjian Li, Hassan Iqbal, Krishna Kumar

There is increasing interest in solving partial differential equations (PDEs) by casting them as machine learning problems. Recently, there has been a spike in exploring Kolmogorov-Arnold Networks (KANs) as an alternative to traditional neural networks represented by Multi-Layer Perceptrons (MLPs). While showing promise, their performance advantages in physics-based problems remain largely unexplored. Several critical questions persist: Can KANs capture complex physical dynamics and under what conditions might they outperform traditional architectures? In this work, we present a comparative study of KANs and MLPs for learning physical systems governed by PDEs. We assess their performance when applied in deep operator networks (DeepONet) and graph network-based simulators (GNS), and test them on physical problems that vary significantly in scale and complexity. Drawing inspiration from the Kolmogorov Representation Theorem, we examine the behavior of KANs and MLPs across shallow and deep network architectures. Our results reveal that although KANs do not consistently outperform MLPs when configured as deep neural networks, they demonstrate superior expressiveness in shallow network settings, significantly outpacing MLPs in accuracy over our test cases. This suggests that KANs are a promising choice, offering a balance of efficiency and accuracy in applications involving physical systems.

📄 PDF Abstract BibTeX arXiv:2504.11397

Code (1)

geoelements-dev/mlp-kan 공식 구현 pytorch

Tasks

Kolmogorov-Arnold Networks

Similar Papers 제목 키워드 기반

KAN: Kolmogorov-Arnold Networks

2024-04-30 · Ziming Liu, YiXuan Wang, Sachin Vaidya, Fabian Ruehle 외

Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("ne…

Kolmogorov-Arnold Networks

Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problems

2024-06-28 · Amanda A. Howard, Bruno Jacob, Sarah H. Murphy, Alexander Heinlein 외

Kolmogorov-Arnold networks (KANs) have attracted attention recently as an alternative to multilayer perceptrons (MLPs) for scientific machine learning. However, KANs can be expensive to train, even for relatively small n…

Kolmogorov-Arnold Networks

On the expressiveness and spectral bias of KANs

2024-10-02 · YiXuan Wang, Jonathan W. Siegel, Ziming Liu, Thomas Y. Hou

Kolmogorov-Arnold Networks (KAN) \cite{liu2024kan} were very recently proposed as a potential alternative to the prevalent architectural backbone of many deep learning models, the multi-layer perceptron (MLP). KANs have …

Kolmogorov-Arnold Networks

Scientific Machine Learning with Kolmogorov-Arnold Networks

2025-07-30 · Salah A. Faroughi, Farinaz Mostajeran, Amin Hamed Mashhadzadeh, Shirko Faroughi arxiv

The field of scientific machine learning, which originally utilized multilayer perceptrons (MLPs), is increasingly adopting Kolmogorov-Arnold Networks (KANs) for data encoding. This shift is driven by the limitations of …

Computational Efficiency

SPIKANs: Separable Physics-Informed Kolmogorov-Arnold Networks

2024-11-09 · Bruno Jacob, Amanda A. Howard, Panos Stinis

Physics-Informed Neural Networks (PINNs) have emerged as a promising method for solving partial differential equations (PDEs) in scientific computing. While PINNs typically use multilayer perceptrons (MLPs) as their unde…

Kolmogorov-Arnold Networks