连接过去与未来：面向时间序列预测的分布感知对齐
Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
AI总结：
本文提出TimeAlign框架，通过简单重建任务对齐辅助特征，提升时间序列预测性能，理论分析证明重建改善泛化能力，对齐增强表示与预测目标的互信息。
摘要：
尽管对比学习等表征学习方法在视觉和自然语言处理中已被长期探索，但其在现代时间序列预测器中的应用仍有限。我们相信这些方法在该领域具有巨大潜力。为释放这一潜力，我们显式对齐过去和未来表示，从而弥合输入历史与未来目标之间的分布差距。为此，我们引入TimeAlign，一个轻量级、即插即用的框架，通过简单的重建任务对齐辅助特征，并将其反馈到任何基础预测器中。在八个基准测试中的广泛实验验证了其优越性能。进一步研究表明，收益主要来自纠正历史输入与未来输出之间的频率不匹配。此外，我们提供了两项理论证明，说明重建如何提高预测泛化能力，以及对齐如何增加学习表示与预测目标之间的互信息。代码可在https://github.com/TROUBADOUR000/TimeAlign获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
