F-KANs: Federated Kolmogorov-Arnold Networks

Engin Zeydan, Cristian J. Vaca-Rubio, Luis Blanco, Roberto Pereira, Marius Caus +1 more
7/29/2024
cs.LGcs.AIcs.CR

No official code found. Best implementation: ezeydan/F-KANs (3 stars, last commit 2024-07-30).

Abstract

In this paper, we present an innovative federated learning (FL) approach that utilizes Kolmogorov-Arnold Networks (KANs) for classification tasks. By utilizing the adaptive activation capabilities of KANs in a federated framework, we aim to improve classification capabilities while preserving privacy. The study evaluates the performance of federated KANs (F- KANs) compared to traditional Multi-Layer Perceptrons (MLPs) on classification task. The results show that the F-KANs model significantly outperforms the federated MLP model in terms of accuracy, precision, recall, F1 score and stability, and achieves better performance, paving the way for more efficient and privacy-preserving predictive analytics.

View on arXivView PDF

Code Implementations(1)

ezeydan/F-KANsCommunity100%

Federated Learning with KAN

30PythonJul 29, 20242 years ago

Similar Papers

Enhancing Federated Learning with Kolmogorov-Arnold Networks: A Comparative Study Across Diverse Aggregation Strategies

91% match2025

A Unified Benchmark of Federated Learning with Kolmogorov-Arnold Networks for Medical Imaging

87% match1 repo2025

Fed-KAN: Federated Learning with Kolmogorov-Arnold Networks for Traffic Prediction

84% match2025

FedPNN: One-shot Federated Classification via Evolving Clustering Method and Probabilistic Neural Network hybrid

84% match2023

AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning

83% match1 repo342025

DP-KAN: Differentially Private Kolmogorov-Arnold Networks

83% match2024

Cite this paper

@article{zeydan2024fkans,
  title  = {F-KANs: Federated Kolmogorov-Arnold Networks},
  author = {Engin Zeydan and Cristian J. Vaca-Rubio and Luis Blanco and Roberto Pereira and Marius Caus and Abdullah Aydeger},
  year   = {2024},
  eprint = {2407.20100},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.20100v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.20100.svg)](https://codeofpaper.com/paper/2407.20100)

Discussion