arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.31129cs.LG
收藏

使用单一算子泛化多尺度时间序列建模

Generalizing Multi-Scale Time-Series Modeling with a Single Operator

School of Electrical Engineering, KAIST, Daejeon, Republic of Korea(韩国成均馆大学电子工程学院);Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea(首尔国立大学计算机科学与工程系)

Cheonwoo Lee, Dooho Lee, Doyun Choi, Jaemin Yoo

AI总结:

提出SiGMA架构,通过可学习离散高斯核实现距离感知缩放,解决现有方法固定离散缩放的局限性,在长期和短期预测任务中均达到最优性能。

摘要:

多尺度建模通过捕获多个分辨率的时间动态,已成为时间序列预测的有效设计原则。由于文献中尚未建立原则性基础,我们将现有的缩放方法统一为一个缩放算子族,揭示了现有方法的一个基本局限性:依赖固定和离散的缩放。为了解决这一局限性,我们提出了SiGMA(单一泛化多尺度架构),它通过基于尺度空间理论的可学习离散高斯(LDG)核实现距离感知缩放。我们在长期和短期预测基准上全面评估了SiGMA,与最先进的多尺度基线进行了比较。SiGMA在两项任务上均优于所有竞争对手,特别是在16个长期评估设置中,有13个达到了最佳性能。除了准确性,SiGMA在训练速度上比最强竞争对手提高了最多5.3倍,内存消耗降低了最多3.8倍。代码可在https://github.com/cheonwoolee/SiGMA获取。

英文摘要:

Multi-scale modeling has emerged as an effective design principle for time-series forecasting by capturing temporal dynamics at multiple resolutions. As no principled foundation has been established in the literature, we unify existing scaling methods into a scaling operator family, revealing a fundamental limitation of existing approaches: reliance on fixed and discrete scaling. To address this limitation, we propose SiGMA (Single Generalized Multi-scale Architecture), which enables distance-aware scaling via the learnable discrete Gaussian (LDG) kernel grounded in scale-space theory. We evaluate SiGMA comprehensively on long- and short-term forecasting benchmarks against state-of-the-art multi-scale baselines. SiGMA outperforms all competitors on both tasks, especially achieving the best performance in 13 out of 16 long-term evaluation settings. Beyond accuracy, SiGMA significantly improves training speed by up to 5.3 times and reduces memory consumption by up to 3.8 times over the strongest competitors. Code is available at https://github.com/cheonwoolee/SiGMA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑