arXiv cs.AI· Yiyang Zhang, Yuli Zheng, Bin Li, Meimei Zhang, Qiang Sun·· 12 小时前AI 评分22
FARR：面向长时程时间序列预测的预测感知残差精炼方法
FARR: Forecast-Aware Residual Refinement with Matched Endpoint Evidence for Long-Horizon Time-Series Forecasting
AI 导读
研究者提出 FARR（Forecast-Aware Residual Refinement），通过对比标准条件与预设空条件下的预测差异获取端点证据，再由共享残差精炼器结合历史特征估计有效预测的剩余误差，并用逐时程门控控制残差贡献。在四个长时程预测基准上，FARR 取得对比方法中最佳的数据集平均 MSE 和 MAE。代码将公开。
正文 · 原文
Abstract:Large language models use auxiliary conditioning to incorporate additional information into time-series forecasts. However, auxiliary conditioning does not consistently improve accuracy and can increase forecasting error when its influence is poorly matched to the observed temporal context. We propose Forecast-Aware Residual Refinement (FARR), which learns to correct forecasts using endpoint evidence. FARR obtains a valid forecast under the standard condition and a null forecast under a predefined null condition. Their difference reveals how conditioning changes the prediction. A shared residual refiner combines this endpoint evidence with historical features to estimate the remaining error of the valid forecast. Horizon-wise gating then controls the contribution of the predicted residual to the final output. Experiments on four long-horizon forecasting benchmarks show that FARR achieves the best dataset-average MSE and MAE among the compared methods. Code will be released at this https URL.
| Comments: | 10 pages, 3 figures, 4 tables |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07870 [cs.AI] |
| (or arXiv:2611.07870v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07870 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhangyiyang Zhang Yiyang [view email]
[v1]
Thu, 5 Nov 2026 11:45:32 UTC (1,364 KB)
来源：arXiv cs.AI · arxiv.org