针对多变量时间序列，按通道独立检索历史片段提升预测精度。
Channel-wise Retrieval for Multivariate Time Series Forecasting
- 为每个变量独立检索历史数据，捕捉不同通道的周期特性。
- 在7个公开数据集上优于现有方法，且推理效率高。
- 适合需要精准建模多变量动态关系的研究与工业场景。
多变量时间序列预测常因固定回溯窗口难以捕捉长程依赖。基于检索的预测通过从记忆中检索历史片段缓解此问题，但现有方法采用通道无关策略，对所有变量使用相同参考，忽略了不同通道在周期性和频谱特征上的差异。本文提出CRAFT（Channel-wise retrieval-augmented forecasting）框架，对每个通道独立进行检索。为保证效率，CRAFT采用两阶段流程：首先在时域构建稀疏关系图以剔除无关候选，再在频域依据谱相似性排序参考，突出主导周期成分并抑制噪声。在七个公开基准上的实验表明，CRAFT显著优于当前最先进方法，在保持实用推理效率的同时实现更高预测精度。
原文摘要 · Abstract (English)
Multivariate time series forecasting often struggles to capture long-range dependencies due to fixed lookback windows. Retrieval-augmented forecasting addresses this by retrieving historical segments from memory, but existing approaches rely on a channel-agnostic strategy that applies the same references to all variables. This neglects inter-variable heterogeneity, where different channels exhibit distinct periodicities and spectral profiles. We propose CRAFT (Channel-wise retrieval-augmented forecasting), a novel framework that performs retrieval independently for each channel. To ensure efficiency, CRAFT adopts a two-stage pipeline: a sparse relation graph constructed in the time domain prunes irrelevant candidates, and spectral similarity in the frequency domain ranks references, emphasizing dominant periodic components while suppressing noise. Experiments on seven public benchmarks demonstrate that CRAFT outperforms state-of-the-art forecasting baselines, achieving superior accuracy with practical inference efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。