paper-with-me

Papers

Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data

2024-10-11 · Arthur Mendonça Sasse, Claudio Miceli de Farias

Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi- Layer Perceptrons (MLPs) with a similar number of parameters for 100 rounds of federated learning in the MNIST classification task using non-IID partitions with 100 clients. After 15 trials for each model, we show that the best accuracies achieved by MLPs can be achieved by Spline-KANs in half of the time (in rounds), with just a moderate increase in computing time.

📄 PDF Abstract BibTeX arXiv:2410.08961

Code (1)

artsasse/fedkan 공식 구현

Tasks

Federated LearningKolmogorov-Arnold Networks

Similar Papers 제목 키워드 기반

F-KANs: Federated Kolmogorov-Arnold Networks

2024-07-29 · Engin Zeydan, Cristian J. Vaca-Rubio, Luis Blanco, Roberto Pereira 외

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 …

ClassificationFederated LearningKolmogorov-Arnold NetworksPrivacy Preserving

CG-FKAN: Compressed-Grid Federated Kolmogorov-Arnold Networks for Communication Constrained Environment

2025-11-03 · Seunghun Yu, Youngjoon Lee, Jinu Gong, Joonhyuk Kang arxiv

Federated learning (FL), widely used in privacy-critical applications, suffers from limited interpretability, whereas Kolmogorov-Arnold Networks (KAN) address this limitation via learnable spline functions. However, exis…

Federated Learning

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

2025-05-12 · Yizhou Ma, Zhuoqin Yang, Luis-Daniel Ibáñez

Multilayer Perceptron (MLP), as a simple yet powerful model, continues to be widely used in classification and regression tasks. However, traditional MLPs often struggle to efficiently capture nonlinear relationships in …

Federated LearningKolmogorov-Arnold NetworksPrivacy Preserving

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

2025-04-28 · YoungJoon Lee, Jinu Gong, Joonhyuk Kang

Federated Learning (FL) enables model training across decentralized devices without sharing raw data, thereby preserving privacy in sensitive domains like healthcare. In this paper, we evaluate Kolmogorov-Arnold Networks…

Federated LearningKolmogorov-Arnold NetworksPrivacy Preserving

KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward

2024-11-15 · Divesh Basina, Joseph Raj Vishal, Aarya Choudhary, Bharatesh Chakravarthi

The curse of dimensionality poses a significant challenge to modern multilayer perceptron-based architectures, often causing performance stagnation and scalability issues. Addressing this limitation typically requires va…

Kolmogorov-Arnold Networks