Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis

TL;DR

This paper evaluates Kolmogorov-Arnold Networks (KAN) for time series classification, demonstrating comparable or superior performance to MLPs and highlighting their robustness advantages due to lower Lipschitz constants.

Contribution

The study provides the first large-scale benchmark validation of KAN on time series data, showing their competitive performance and robustness benefits over traditional MLPs.

Findings

KAN achieves comparable or better accuracy than MLP on 128 datasets.

Ablation study shows output mainly depends on the base component.

KAN and hybrid models exhibit enhanced robustness due to lower Lipschitz constants.

Abstract

Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical appeal, KAN require validation on large-scale benchmark datasets. Time series data, which has become increasingly prevalent in recent years, especially univariate time series are naturally suited for validating KAN. Therefore, we conducted a fair comparison among KAN, MLP, and mixed structures. The results indicate that KAN can achieve performance comparable to, or even slightly better than, MLP across 128 time series datasets. We also performed an ablation study on KAN, revealing that the output is primarily determined by the base component instead of b-spline function. Furthermore, we assessed the robustness of these models and found that KAN and the hybrid structure MLP\_KAN exhibit significant robustness advantages, attributed to their lower Lipschitz constants. This suggests that KAN and KAN layers hold strong potential to be robust models or to improve the adversarial robustness of other models.