arXiv：cs.LG· Jung Min Choi, Ngoc Son Le, Ibram Abdelmalak, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme·· 3 小时前AI 评分27
DuoTS：面向时间序列预测的双上下文类比检索模型
Dual-Context Analog Retrieval for Time Series Forecasting
AI 导读
DuoTS 是一种双上下文时间序列预测模型，先由并行 patch 编码器与线性预测头生成基础预测，再逐个未来 patch 逐步精修。每次精修结合关注近期 token 的当前上下文，以及提供检索类比及其后续轨迹的细节上下文，从而按时间距离为各未来片段匹配证据。在多个真实数据集上 DuoTS 达到 SOTA，消融实验验证了两种上下文的贡献，且该精修机制与模型无关，可集成进现有预测模型。
正文
Abstract:Most long-term time-series forecasting models map the look-back window directly to the full horizon in a single pass. While efficient, this design does not explicitly identify which historical states are most relevant to different future segments or exploit what followed those states. Analog forecasting addresses this by retrieving past states similar to the present and using their observed continuations, but single nearest matches can be unreliable and overlapping patches may produce redundant candidates. We propose DuoTS, a Dual-Context Time Series forecasting model that uses retrieved evidence without relying on it exclusively. DuoTS first produces a base forecast with a parallel patch encoder and linear prediction head, then progressively refines it one future patch at a time. Each refinement combines two views: a current context that attends to recent tokens and captures the latest dynamics, and a detail context that provides distinct retrieved analogs together with their subsequent trajectories. Patch-wise refinement allows the model to balance these views across the forecast horizon and associate each future segment with evidence appropriate to its temporal distance from the present. Experiments on multiple real-world datasets show that DuoTS achieves state-of-the-art performance, while ablations confirm the contribution of each context. The refinement mechanism is also model-agnostic, requiring only an encoded look-back window and the future-patch position, and can therefore be integrated into existing forecasting models.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03491 [cs.LG] |
| (or arXiv:2610.03491v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03491 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jung Min Choi [view email]
[v1]
Fri, 2 Oct 2026 15:54:56 UTC (232 KB)
来源：arXiv：cs.LG · arxiv.org