发表机构
Applied AI Institute（应用人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DecoVAE是一种轻量级可解释的趋势-季节VAE框架，通过分解时间序列的趋势与季节组件解决概率时间序列预测的局限，在7个真实基准上精度优于基线且效率显著提升。
AI 中文摘要
概率时间序列预测仍然具有挑战性，很大程度上是因为对不同的趋势和季节动态进行建模需要专门的方法。现有方法往往无法捕捉这些组件的独特内部属性、缺乏可解释性，或存在内存和运行时开销大的问题。为解决这些局限，我们提出DecoVAE——一种轻量级可解释的趋势-季节VAE框架，该框架通过应用领域特定的归纳偏置，将时间序列明确分解为趋势和季节组件。趋势流对潜在轨迹应用差分正则化器以强制结构平滑，类似于Hodrick-Prescott滤波器；同时，季节流通过复高斯VAE在频域中运行，原生捕获周期模式的振幅和相位。在7个真实基准上的广泛评估显示，DecoVAE始终优于强大的基线方法：对于短期预测，它在CRPS上实现了最高14.96%的降低，在NMAE上实现了最高23.30%的降低；对于长期预测，这两个指标的降低幅度分别达到52.68%和26.51%。关键的是，DecoVAE在获得这些精度提升的同时保持了极高的效率，与次优方法相比，它的模型权重最多减少93%，速度最多提升74%。
英文摘要
Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches. Existing methods often fail to capture the unique inner properties of these components, lack interpretability, or suffer from heavy memory and runtime overhead. To address these limitations, we propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework that explicitly decomposes time series into trend and seasonal components by applying domain-specific inductive biases. The trend stream enforces structural smoothness using a differential regularizer on the latent trajectory, analogous to the Hodrick-Prescott filter. Concurrently, the seasonal stream operates in the frequency domain via a complex Gaussian VAE, natively capturing the amplitude and phase of periodic patterns. Extensive evaluations across seven real-world benchmarks show that DecoVAE consistently outperforms strong baselines. It achieves reductions of up to 14.96\% in CRPS and 23.30\% in NMAE for short-term forecasting, and up to 52.68\% and 26.51\% for long-term horizons. Crucially, DecoVAE yields these accuracy gains while remaining highly efficient, reducing model weight by up to 93\% and accelerating speed by up to 74\% compared to the second-best method.
