Recent Transformer- and MLP-based models have demonstrated strong performance in long-term time series forecasting, yet Transformers remain limited by their quadratic complexity and permutation-equivariant attention, while MLPs exhibit spectral bias. We propose HaKAN, a versatile model based on Kolmogorov-Arnold Networks (KANs), leveraging Hahn polynomial-based learnable activation functions and providing a lightweight and interpretable alternative for multivariate time series forecasting. Our model integrates channel independence, patching, a stack of Hahn-KAN blocks with residual connections, and a bottleneck structure comprised of two fully connected layers. The Hahn-KAN block consists of inter- and intra-patch KAN layers to effectively capture both global and local temporal patterns. Extensive experiments on various forecasting benchmarks demonstrate that our model consistently outperforms recent state-of-the-art methods, with ablation studies validating the effectiveness of its core components.

翻译：近期基于Transformer和MLP的模型在长期时间序列预测中展现出强大性能，但Transformer仍受限于其二次复杂度与置换等变注意力机制，而MLP则存在频谱偏差。我们提出HaKAN，一种基于Kolmogorov-Arnold网络（KANs）的通用模型，利用基于Hahn多项式的可学习激活函数，为多元时间序列预测提供了一种轻量且可解释的替代方案。该模型整合了通道独立性、分块处理、具有残差连接的Hahn-KAN块堆叠，以及由两个全连接层构成的瓶颈结构。Hahn-KAN块包含块间与块内KAN层，以有效捕捉全局与局部时间模式。在多种预测基准上的大量实验表明，本模型持续优于近期最先进方法，消融研究验证了其核心组件的有效性。