This paper introduces a novel application of Kolmogorov-Arnold Networks (KANs) to time series forecasting, leveraging their adaptive activation functions for enhanced predictive modeling. Inspired by the Kolmogorov-Arnold representation theorem, KANs replace traditional linear weights with spline-parametrized univariate functions, allowing them to learn activation patterns dynamically. We demonstrate that KANs outperforms conventional Multi-Layer Perceptrons (MLPs) in a real-world satellite traffic forecasting task, providing more accurate results with considerably fewer number of learnable parameters. We also provide an ablation study of KAN-specific parameters impact on performance. The proposed approach opens new avenues for adaptive forecasting models, emphasizing the potential of KANs as a powerful tool in predictive analytics.

翻译：本文介绍了一种将Kolmogorov-Arnold网络（KANs）应用于时间序列预测的新方法，利用其自适应激活函数来增强预测建模能力。受Kolmogorov-Arnold表示定理启发，KANs用样条参数化的单变量函数替代传统的线性权重，从而能够动态学习激活模式。我们通过真实世界的卫星流量预测任务证明，KANs在可学习参数数量显著减少的情况下，其性能优于传统的多层感知机（MLPs），并能提供更精确的结果。我们还对KANs特有参数对性能的影响进行了消融研究。所提出的方法为自适应预测模型开辟了新途径，凸显了KANs作为预测分析强大工具的潜力。