Kolmogorov-Arnold Fourier Networks

2025-02-09 · Jusheng Zhang, Yijia Fan, Kaitong Cai, Keze Wang

Although Kolmogorov-Arnold based interpretable networks (KAN) have strong theoretical expressiveness, they face significant parameter explosion and high-frequency feature capture challenges in high-dimensional tasks. To address this issue, we propose the Kolmogorov-Arnold-Fourier Network (KAF), which effectively integrates trainable Random Fourier Features (RFF) and a novel hybrid GELU-Fourier activation mechanism to balance parameter efficiency and spectral representation capabilities. Our key technical contributions include: (1) merging KAN's dual-matrix structure through matrix association properties to substantially reduce parameters; (2) introducing learnable RFF initialization strategies to eliminate spectral distortion in high-dimensional approximation tasks; (3) implementing an adaptive hybrid activation function that progressively enhances frequency representation during the training process. Comprehensive experiments demonstrate the superiority of our KAF across various domains including vision, NLP, audio processing, and differential equation-solving tasks, effectively combining theoretical interpretability with practical utility and computational efficiency.

📄 PDF Abstract BibTeX arXiv:2502.06018

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Methods 이 논문이 사용한 방법론

KAF A Kernel Activation Function is a non-parametric activation function defined as a one-dimensional kernel approximator: $$ f(s) = \sum_{i=1}^D \alpha_i \kappa( s, d_i)…

KA-GNN: Kolmogorov-Arnold Graph Neural Networks for Molecular Property Prediction

2024-10-15 · Longlong Li, YiPeng Zhang, Guanghui Wang, Kelin Xia

As key models in geometric deep learning, graph neural networks have demonstrated enormous power in molecular data analysis. Recently, a specially-designed learning scheme, known as Kolmogorov-Arnold Network (KAN), shows…

Drug Discovery Graph Attention Graph Neural Network Molecular Property Prediction+1

Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection

2025-11-19 · Xiancheng Wang, Lin Wang, Rui Wang, Zhibo Zhang 외 arxiv

Time-series anomaly detection plays a critical role in numerous real-world applications, including industrial monitoring and fault diagnosis. Recently, Mamba-based state-space models have shown remarkable efficiency in l…

Anomaly Detection Fault Diagnosis

Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks

2025-08-01 · Sergei Gleyzer, Hanh Nguyen, Dinesh P. Ramakrishnan, Eric A. F. Reinhardt arxiv

The Kolmogorov-Arnold representation theorem states that any continuous multivariable function can be exactly represented as a finite superposition of continuous single variable functions. Subsequent simplifications of t…

FourierKAN-GCF: Fourier Kolmogorov-Arnold Network -- An Effective and Efficient Feature Transformation for Graph Collaborative Filtering

2024-06-03 · Jinfeng Xu, Zheyu Chen, Jinze Li, Shuo Yang 외

Graph Collaborative Filtering (GCF) has achieved state-of-the-art performance for recommendation tasks. However, most GCF structures simplify the feature transformation and nonlinear operation during message passing in t…

Collaborative Filtering

Implicit Neural Representations with Fourier Kolmogorov-Arnold Networks

2024-09-14 · Ali Mehrabian, Parsa Mojarad Adi, Moein Heidari, Ilker Hacihaliloglu

Implicit neural representations (INRs) use neural networks to provide continuous and resolution-independent representations of complex signals with a small number of parameters. However, existing INR models often fail to…

Kolmogorov-Arnold Networks SSIM