用未来预测反哺当前，提升长期时间序列预测稳定性
Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting
- 通过前瞻增强与并行自修正，优化基础模型预测
- 最长可提升58%准确率，且在次优训练下仍稳定改进
- 无需复杂结构，适合对精度要求高的工业时序场景
长期时间序列预测（LTSF）因并行效率与时序一致性之间的权衡而面临挑战。直接多步预测（DMS）虽能快速并行生成所有未来步长的预测，但常丧失步间时序一致性；迭代多步预测（IMS）虽保留时序依赖，却存在误差累积和推理缓慢的问题。为此，我们提出Back to the Future（BTTF）框架，通过前瞻增强与自校正精炼，显著提升预测稳定性。该方法不依赖复杂模型结构，而是将初始预测结果作为增强信号，集成第二阶段模型进行优化。尽管方法简单，但能持续提升长程预测精度，在最坏情况下仍实现最高58%的准确率提升，并在基础模型训练条件不佳时保持稳定改进。结果表明，利用模型自身生成的预测作为增强信号，是一种简单而强大的长周期预测优化方式。
原文摘要 · Abstract (English)
Long-term time series forecasting (LTSF) remains challenging due to the trade-off between parallel efficiency and sequential modeling of temporal coherence. Direct multi-step forecasting (DMS) methods enable fast, parallel prediction of all future horizons but often lose temporal consistency across steps, while iterative multi-step forecasting (IMS) preserves temporal dependencies at the cost of error accumulation and slow inference. To bridge this gap, we propose Back to the Future (BTTF), a simple yet effective framework that enhances forecasting stability through look-ahead augmentation and self-corrective refinement. Rather than relying on complex model architectures, BTTF revisits the fundamental forecasting process and refines a base model by ensembling the second-stage models augmented with their initial predictions. Despite its simplicity, our approach consistently improves long-horizon accuracy and mitigates the instability of linear forecasting models, achieving accuracy gains of up to 58% and demonstrating stable improvements even when the first-stage model is trained under suboptimal conditions. These results suggest that leveraging model-generated forecasts as augmentation can be a simple yet powerful way to enhance long-term prediction, even without complex architectures.
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。