用KAN动态选频，提升长时序预测精度
KFS: KAN based adaptive Frequency Selection learning architecture for long term time series forecasting
- 基于KAN构建自适应频率选择模块，从频谱中选主导频率
- 在多个真实数据集上超越现有方法，实现最佳预测性能
- 适合需要高精度长时序建模的工业与金融场景
多尺度分解架构已成为时间序列预测的主流方法。然而，现实世界的时间序列在不同尺度上存在噪声干扰，且各尺度频率成分的信息分布异质性导致多尺度表征不佳。受柯尔莫哥洛夫-阿诺德网络（KAN）和帕塞瓦尔定理启发，我们提出一种基于KAN的自适应频率选择学习架构（KFS），以应对这些挑战。该框架通过频域能量分布实现主导频率选择的FreK模块，缓解跨尺度噪声干扰，并利用KAN实现复杂模式表达；时间戳嵌入对齐机制同步各尺度的时序表示。特征混合模块将各尺度模式与对齐后的时序特征融合。在多个真实时间序列数据集上的大量实验表明，KFS作为简单而有效的架构，达到了当前最优性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。