RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting

Researchers introduced RACE (Residual-Aware Correction of Forecasting Errors), a two-stage test-time adaptation framework that improves time-series foundation model (TSFM) forecasting by using same-domain neighbor evidence without modifying the backbone. Across four TSFMs, RACE improved all three domain-aggregate metrics on both primary domains, with the largest gains on high-error queries, and a Gate trained on one TSFM transferred to other backbones without adaptation, improving all 72 cross-backbone metric comparisons over matched frozen targets. The work targets neighbor-rich settings such as continuous glucose monitoring (CGM) and Web/cloud workloads, where related but nonidentical historical series are available for each query.

arXiv:2610.00405v1 Announce Type: new 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.