F-KANs: Federated Kolmogorov-Arnold Networks

TL;DR

The results show that the F-KANs model significantly outperforms the F-MLP model in terms of accuracy, precision, recall, recall, F1 score and stability, and achieves better performance, paving the way for more efficient and privacy-preserving predictive analytics.

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.

Figures (3)

• Figure 1: Federated KAN Methodology
• Figure 2: Comparisons of federated learning with F-KAN model and F-MLP model over rounds (a) Cross-Entropy loss. (b) Accuracy
• Figure 3: Comparisons of federated learning with F-KAN model and F-MLP model over rounds (a) Precision. (b) Recall. (c) F1-Score