时间序列预测中测试时自适应的校正空间跨变量交互
Correction-space Cross-variate Interaction for Test-time Adaptation in Time Series Forecasting
查看机构详情
- Eindhoven University of Technology（埃因霍温理工大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
提出CoRe方法，通过在校正空间而非预测空间进行跨变量交互，利用共享锚点细化和谱门控，在时间序列预测测试时自适应中显著降低MSE。
中文摘要 AI 辅助
测试时自适应（TTA）是处理时间序列预测（TSF）中分布偏移的一种有前景的范式，其中模型在推理时进行自适应，通常利用延迟的观测数据来改进预测。在多变量设置中，分布偏移通常表现出跨变量依赖性，然而现有的TSF-TTA方法独立地适应每个变量，忽略了这种跨变量结构。利用这种结构激发了跨变量交互，但通过骨干预测耦合变量会引入跨变量混合未校正误差的直接路径，这在TSF-TTA的延迟监督下是一个担忧。我们确定交互空间是一个关键的设计选择，并表明作用于改进骨干输出的适配器校正（即校正空间）而非预测本身，可以避免跨变量直接传播骨干误差。我们在此基础上提出CoRe（校正空间交互细化），通过（i）共享锚点校正细化（SCR）实现校正空间交互，该机制通过参数高效瓶颈将每个变量的校正与共享锚点结合，以及（ii）输入条件谱门控，自适应地调节来自当前输入窗口的细化。在七个骨干、六个数据集和四个预测范围上，CoRe在骨干上平均降低MSE 25.82%，在最先进的TSF-TTA方法上降低10.57%，在中长期范围内增益更强，计算开销适中。数据和代码可在以下网址获取：此https URL
英文摘要
Test-time adaptation (TTA) is a promising paradigm for handling distribution shift in time-series forecasting (TSF), where models adapt at inference time, often leveraging delayed observed data to refine predictions. In the multivariate setting, distribution shifts often exhibit cross-variate dependencies, yet existing TSF-TTA methods adapt each variate independently and ignore this cross-variate structure. Exploiting such structure motivates cross-variate interaction, but coupling variates through backbone predictions introduces direct pathways for mixing uncorrected errors across variates, a concern under the delayed supervision of TSF-TTA. We identify the \emph{interaction space} as a key design choice, and show that acting on adapter corrections that refine backbone outputs, the \emph{correction space}, rather than on the predictions themselves, avoids directly propagating backbone errors across variates. We build on this to propose \textsc{CoRe} (\textsc{Co}rrection-space Interaction \textsc{Re}finement), realizing correction-space interaction through (i) Shared-anchor Correction Refinement (SCR), which combines each variate's correction with a shared anchor through a parameter-efficient bottleneck, and (ii) input-conditioned spectral gating, which adaptively modulates the refinement from the current input window. Across seven backbones, six datasets, and four prediction horizons, \textsc{CoRe} reduces MSE by 25.82\% on average over backbones and 10.57\% over the state-of-the-art TSF-TTA method, with stronger gains at medium-to-long horizons and modest computational overhead. Data and code are available at: https://github.com/yyddou/CoReTTA
