发表机构
Nanjing University; National Key Laboratory for Novel Software Technology, Nanjing University（南京大学; 南京大学计算机软件新技术全国重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对邻居丰富的时间序列预测中邻居残差冲突问题，提出RACE两阶段框架，通过检索对齐邻居残差并训练轻量门控，在不修改骨干网络下提升四个TSFM在两个域上的全部指标。
AI 中文摘要
时间序列基础模型（TSFMs）在各种预测任务中表现强劲，但其逐序列推理方式不适合邻居丰富的预测场景，在该场景中，每个查询都可访问相关但不完全相同的历史序列。连续血糖监测（CGM）和Web/云工作负载是此类场景的典型代表：CGM轨迹共享生理模式，但在个体、设备和条件上存在差异；而Web/云工作负载则结合了常见运行状态与非平稳性、重尾分布和突发性。这些历史数据具有有用的结构，但邻居并非同等相关。现有方法要么为每个目标域微调TSFM，产生额外成本且跨骨干网络的迁移性有限；要么直接附加检索到的序列而不验证其是否支持当前预测。关键挑战在于来自邻居序列的冲突残差证据，以及不同TSFM和预测任务间残差模式的差异。我们提出了测试时邻域缩放：在不修改骨干网络的情况下利用同域邻居证据。我们提出RACE（残差感知预测误差校正），一个利用历史邻居的两阶段框架。首先，我们检索与查询兼容的邻居，将其残差对齐到查询尺度，并将一致证据聚合到无需训练的RACE-TF校正中。完整的RACE使用轻量级、域特定的门控来决定何时应用校正有益，并提供跨TSFM骨干网络的可复用训练流程。在四个TSFM上，RACE在两个主要域上均提升了所有三个域聚合指标，其中高误差查询的改进最大。在每个域内，在一个TSFM上训练的门控可迁移到其他骨干网络而无需适应，所得流程在所有72个跨骨干网络指标比较中均优于匹配的冻结目标。
英文摘要
Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich forecasting, where each query has access to related but nonidentical historical series. Continuous glucose monitoring (CGM) and Web/cloud workloads exemplify this setting: CGM trajectories share physiological patterns but vary across individuals, devices, and conditions, while Web/cloud workloads combine common operating regimes with non-stationarity, heavy tails, and bursts. These histories share useful structure, yet neighbors are not equally relevant. Existing methods either fine-tune TSFMs for each target domain, incurring additional costs and offering limited transferability across backbones, or append retrieved series without verifying whether they support the current forecast. The key challenges are conflicting residual evidence from neighboring series and residual patterns that vary across TSFMs and forecasting tasks. We formulate test-time neighborhood scaling: using same-domain neighbor evidence without modifying the backbone. We propose RACE (Residual-Aware Correction of Forecasting Errors), a two-stage framework for using historical neighbors. We first retrieve query-compatible neighbors, align their residuals to the query scale, and aggregate coherent evidence into the training-free RACE-TF correction. Full RACE then uses a lightweight, domain-specific Gate to determine when applying the correction is beneficial, with a reusable training workflow across TSFM backbones. Across four TSFMs, RACE improves all three domain-aggregate metrics on both primary domains, with the largest gains on high-error queries. Within each domain, a Gate trained on one TSFM transfers to other backbones without adaptation, and the resulting pipeline improves all 72 cross-backbone metric comparisons over the matched frozen targets.
Comments25 pages including references and appendices; 8 figures
