Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis
This work provides empirical validation for KAN on time series data, addressing a gap for researchers in machine learning and time series analysis, though it is incremental as it applies an existing method to new data.
The paper tackled validating Kolmogorov-Arnold Networks (KAN) on time series classification, showing that KAN achieves performance comparable to or slightly better than MLPs across 128 datasets, with KAN and hybrid structures exhibiting significant robustness advantages due to lower Lipschitz constants.
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.