An Innovative Networks in Federated Learning

TL;DR

This paper introduces Wavelet Kolmogorov-Arnold Networks (Wav-KAN) for federated learning, leveraging wavelet transforms to improve interpretability, speed, and accuracy across heterogeneous data distributions.

Contribution

The paper develops and applies Wav-KAN with wavelet-based activation functions in federated learning, demonstrating significant performance improvements over existing methods.

Findings

Wav-KAN achieves higher accuracy and interpretability.

Wavelet transforms improve computational speed.

Enhanced robustness and scalability in federated models.

Abstract

This paper presents the development and application of Wavelet Kolmogorov-Arnold Networks (Wav-KAN) in federated learning. We implemented Wav-KAN \cite{wav-kan} in the clients. Indeed, we have considered both continuous wavelet transform (CWT) and also discrete wavelet transform (DWT) to enable multiresolution capabaility which helps in heteregeneous data distribution across clients. Extensive experiments were conducted on different datasets, demonstrating Wav-KAN's superior performance in terms of interpretability, computational speed, training and test accuracy. Our federated learning algorithm integrates wavelet-based activation functions, parameterized by weight, scale, and translation, to enhance local and global model performance. Results show significant improvements in computational efficiency, robustness, and accuracy, highlighting the effectiveness of wavelet selection in scalable neural network design.