TSKANMixer: Kolmogorov-Arnold Networks with MLP-Mixer Model for Time Series Forecasting

TL;DR

This paper introduces TSKANMixer, a novel time series forecasting model combining Kolmogorov-Arnold Networks with the MLP-Mixer architecture, demonstrating improved accuracy over existing models across multiple datasets.

Contribution

The paper proposes integrating Kolmogorov-Arnold Networks into the TSMixer architecture, offering a new approach that enhances forecasting performance in time series analysis.

Findings

TSKANMixer outperforms original TSMixer in accuracy.

KAN layers provide a promising alternative to traditional MLPs.

Model ranks among top performers across datasets.

Abstract

Time series forecasting has long been a focus of research across diverse fields, including economics, energy, healthcare, and traffic management. Recent works have introduced innovative architectures for time series models, such as the Time-Series Mixer (TSMixer), which leverages multi-layer perceptrons (MLPs) to enhance prediction accuracy by effectively capturing both spatial and temporal dependencies within the data. In this paper, we investigate the capabilities of the Kolmogorov-Arnold Networks (KANs) for time-series forecasting by modifying TSMixer with a KAN layer (TSKANMixer). Experimental results demonstrate that TSKANMixer tends to improve prediction accuracy over the original TSMixer across multiple datasets, ranking among the top-performing models compared to other time series approaches. Our results show that the KANs are promising alternatives to improve the performance of time series forecasting by replacing or extending traditional MLPs.