arXiv：cs.LG· Hao-Nan Shi, Tong Wu, Chen-Cong Sun, Yuan Jiang, Han-Jia Ye, De-Chuan Zhan·· 2 天前AI 评分32
RACE：面向邻居丰富场景的时间序列基础模型预测的残差感知测试时自适应
RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting
AI 导读
研究者提出 RACE（Residual-Aware Correction of Forecasting Errors）两阶段框架，在不修改时间序列基础模型（TSFM）主干的前提下，利用同域邻居序列的残差证据进行测试时校正。
正文
Abstract: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.
| Comments: | 25 pages including references and appendices; 8 figures |
| Subjects: | Machine Learning (cs.LG); Machine Learning (stat.ML) |
| Cite as: | arXiv:2610.00405 [cs.LG] |
| (or arXiv:2610.00405v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00405 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tong Wu [view email]
[v1]
Wed, 30 Sep 2026 13:14:38 UTC (1,816 KB)
来源：arXiv：cs.LG · arxiv.org