ROAR：面向零样本时间序列预测的检索机会感知精炼框架

View PDF HTML (experimental)

Abstract:Retrieval augmentation provides time series forecasters with historical continuations, yet even candidates that outperform the base forecast may fail to improve the final prediction. We propose ROAR, a Retrieval Opportunity-Aware Refinement framework for zero-shot time series forecasting. To better exploit these improvement opportunities, its training objective allocates additional emphasis across queries based on base-forecast difficulty and the relative improvement offered by retrieved candidates. Using this objective, ROAR first learns to aggregate aligned historical candidates and uses a learned gate to control their correction strength against a fixed base forecaster. It then jointly calibrates the forecasting module and gate to coordinate their contributions, while anchoring the combined prediction to the first-stage refined output. We derive exact decompositions of refinement gains and the opportunity-weighted training loss, and characterize additional gains from joint calibration under a local linearization. Experiments on seven benchmarks show that ROAR achieves the lowest average MSE among the compared methods. Further evaluations demonstrate average forecasting improvements across multiple backbone families and retrieval-augmented forecasters.

Submission history

From: Jinjin Chi [view email]
[v1] Sun, 24 May 2026 07:31:55 UTC (9,550 KB)
[v2] Thu, 8 Oct 2026 02:36:07 UTC (103 KB)