KFS: KAN based adaptive Frequency Selection learning architecture for long term time series forecasting

TL;DR

The paper introduces KFS, a novel adaptive frequency selection architecture based on KAN, which improves long-term time series forecasting by effectively handling noise and complex patterns across multiple scales.

Contribution

It proposes a new spectral domain frequency selection method and a multi-scale pattern representation framework inspired by KAN and Parseval's theorem.

Findings

Achieves state-of-the-art forecasting accuracy on multiple datasets.

Effectively handles noise interference across different scales.

Provides a simple yet powerful architecture for long-term time series prediction.

Abstract

Multi-scale decomposition architectures have emerged as predominant methodologies in time series forecasting. However, real-world time series exhibit noise interference across different scales, while heterogeneous information distribution among frequency components at varying scales leads to suboptimal multi-scale representation. Inspired by Kolmogorov-Arnold Networks (KAN) and Parseval's theorem, we propose a KAN based adaptive Frequency Selection learning architecture (KFS) to address these challenges. This framework tackles prediction challenges stemming from cross-scale noise interference and complex pattern modeling through its FreK module, which performs energy-distribution-based dominant frequency selection in the spectral domain. Simultaneously, KAN enables sophisticated pattern representation while timestamp embedding alignment synchronizes temporal representations across scales. The feature mixing module then fuses scale-specific patterns with aligned temporal features. Extensive experiments across multiple real-world time series datasets demonstrate that KT achieves state-of-the-art performance as a simple yet effective architecture.