Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and attributes predictions to learnable frequency components. \textsc{FreqLens} introduces two key innovations: (1) \emph{learnable frequency discovery} -- frequency bases are parameterized via sigmoid mapping and learned from data with diversity regularization, enabling automatic discovery of dominant periodic patterns without domain knowledge; and (2) \emph{axiomatic frequency attribution} -- a theoretically grounded framework that provably satisfies Completeness, Faithfulness, Null-Frequency, and Symmetry axioms, with per-frequency attributions equivalent to Shapley values. On Traffic and Weather datasets, \textsc{FreqLens} achieves competitive or superior performance while discovering physically meaningful frequencies: all 5 independent runs discover the 24-hour daily cycle ($24.6 \pm 0.1$h, 2.5\% error) and 12-hour half-daily cycle ($11.8 \pm 0.1$h, 1.6\% error) on Traffic, and weekly cycles ($10\times$ longer than the input window) on Weather. These results demonstrate genuine frequency-level knowledge discovery with formal theoretical guarantees on attribution quality.

翻译：时间序列预测模型通常缺乏可解释性，这限制了其在需要可解释预测的领域中的应用。我们提出 \textsc{FreqLens}，一个可解释的预测框架，它能够发现可学习的频率分量并将预测结果归因于这些分量。\textsc{FreqLens} 引入了两个关键创新：(1) \emph{可学习的频率发现}——频率基通过 sigmoid 映射进行参数化，并通过多样性正则化从数据中学习，从而无需领域知识即可自动发现主导的周期性模式；(2) \emph{公理化的频率归因}——一个具有理论基础的框架，可证明满足完备性、忠实性、零频率和对称性公理，其逐频率归因等价于沙普利值。在交通和天气数据集上，\textsc{FreqLens} 在发现具有物理意义的频率的同时，实现了具有竞争力或更优的性能：所有 5 次独立运行均在交通数据集上发现了 24 小时的日周期（$24.6 \pm 0.1$ 小时，误差 2.5%）和 12 小时的半日周期（$11.8 \pm 0.1$ 小时，误差 1.6%），并在天气数据集上发现了周周期（比输入窗口长 $10\times$）。这些结果证明了在具有归因质量正式理论保证的前提下，实现了真正的频率级知识发现。