提出通用纠错模型，有效缓解深度时序预测中的误差累积问题。
Reviving Error Correction in Modern Deep Time-Series Forecasting
- 分离趋势与季节成分，分别校正预测误差
- 在10个数据集上提升4种模型的长期预测准确率
- 无需重训练，可适配任意现有时序模型
现代深度学习模型在时序预测中表现优异，但在长程预测中因自回归推理导致误差累积而性能下降。尽管传统误差校正机制（ECMs）在统计方法中广泛应用，却难以有效用于深度模型。本文重新审视这一问题，提出一种架构无关的通用误差校正模型——带趋势-季节分解的通用误差校正器（UEC-STD）。该模型通过显式分解预测为趋势与季节成分，并分别训练校正器进行调整。实验表明，UEC-STD在4种骨干模型和10个数据集上显著提升校正精度与鲁棒性。该方法无需重新训练，可直接集成于现有模型，为缓解自回归误差提供实用工具，并带来新见解。代码已开源：https://github.com/DA2I2-SLM/UEC-STD。
原文摘要 · Abstract (English)
Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to error accumulation in autoregressive inference, where predictions are recursively used as inputs. While classical error correction mechanisms (ECMs) have long been used in statistical methods, their applicability to deep learning models remains limited or ineffective. In this work, we revisit the error accumulation problem in deep time-series forecasting and investigate the role and necessity of ECMs in this new context. We propose a simple, architecture-agnostic error correction model that can be integrated with any existing forecaster without requiring retraining. By explicitly decomposing predictions into trend and seasonal components and training the corrector to adjust each separately, we introduce the Universal Error Corrector with Seasonal-Trend Decomposition (UEC-STD), which significantly improves correction accuracy and robustness across 4 backbones and 10 datasets. Our findings provide a practical tool for enhancing forecasts while offering new insights into mitigating autoregressive errors in deep time-series models. Code is available at https://github.com/DA2I2-SLM/UEC-STD.
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。