通过重建对齐历史与未来特征，提升时间序列预测精度。
Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
- 用重建任务对齐历史与未来表示，消除分布差异。
- 在8个基准上实现更优性能，关键提升来自频率匹配修正。
- 理论证明重建增强泛化性，对齐提升表示与目标互信息。
尽管对比学习等表征学习方法在视觉和自然语言处理中广泛应用，但在现代时间序列预测模型中仍较少使用。我们认为其在该领域具有巨大潜力。为释放这一潜力，我们显式对齐历史与未来表示，弥合输入历史与未来目标之间的分布差距。为此，我们提出TimeAlign——一种轻量级、可即插即用的框架，通过简单的重建任务对齐辅助特征，并将结果反馈给任意基础预测器，建立了一种区别于对比学习的新表征范式。在八个基准上的大量实验验证了其优越性能。进一步研究显示，性能提升主要源于修正历史输入与未来输出间的频率不匹配问题。此外，我们提供了两个理论解释：重建如何提升预测泛化能力，以及对齐如何增加学习表示与预测目标之间的互信息。代码已公开于https://github.com/TROUBADOUR000/TimeAlign。
原文摘要 · Abstract (English)
Although contrastive and other representation-learning methods have long been explored in vision and NLP, their adoption in modern time series forecasters remains limited. We believe they hold strong promise for this domain. To unlock this potential, we explicitly align past and future representations, thereby bridging the distributional gap between input histories and future targets. To this end, we introduce TimeAlign, a lightweight, plug-and-play framework that establishes a new representation paradigm, distinct from contrastive learning, by aligning auxiliary features via a simple reconstruction task and feeding them back into any base forecaster. Extensive experiments across eight benchmarks verify its superior performance. Further studies indicate that the gains arise primarily from correcting frequency mismatches between historical inputs and future outputs. Additionally, we provide two theoretical justifications for how reconstruction improves forecasting generalization and how alignment increases the mutual information between learned representations and predicted targets. The code is available at https://github.com/TROUBADOUR000/TimeAlign.
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。