arXiv 2409.184792024-10-15cs.LG

CycleNet：通过建模周期性模式增强时间序列预测

CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns

School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）；Pengcheng Laboratory（鹏城实验室）；The Chinese University of Hong Kong（香港中文大学）；College of Information Science and Technology, Jinan University（暨南大学信息科学技术学院）

Shengsheng Lin, Weiwei Lin, Xinyi Hu, Wentai Wu, Ruichao Mo, Haocheng Zhong

备注：: NeurIPS 2024 Spotlight

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 CycleNet，通过残差周期预测（RCF）技术显式建模时间序列周期性并结合 Linear 或浅层 MLP 进行预测，在多领域实现最优精度且大幅减少参数，作为即插即用技术还能提升现有模型性能。

摘要：

时间序列数据中存在的稳定周期性模式是进行长期预测的基础。在本文中，我们率先探索显式建模这种周期性，以提升模型在长期时间序列预测（LTSF）任务中的性能。具体而言，我们引入了残差周期预测（RCF）技术，该技术利用可学习的循环周期来建模序列内固有的周期性模式，随后对已建模周期的残差成分进行预测。将 RCF 与 Linear 层或浅层 MLP 相结合，构成了本文提出的简单而强大的方法，称为 CycleNet。CycleNet 在电力、天气和能源等多个领域实现了最先进的预测精度，同时通过减少超过 90% 的所需参数量提供了显著的效率优势。此外，作为一种新颖的即插即用技术，RCF 还能显著提升现有模型的预测精度，包括 PatchTST 和 iTransformer。源代码可在 https://github.com/ACAT-SCUT/CycleNet 获取。

英文摘要：

The stable periodic patterns present in time series data serve as the foundation for conducting long-horizon forecasts. In this paper, we pioneer the exploration of explicitly modeling this periodicity to enhance the performance of models in long-term time series forecasting (LTSF) tasks. Specifically, we introduce the Residual Cycle Forecasting (RCF) technique, which utilizes learnable recurrent cycles to model the inherent periodic patterns within sequences, and then performs predictions on the residual components of the modeled cycles. Combining RCF with a Linear layer or a shallow MLP forms the simple yet powerful method proposed in this paper, called CycleNet. CycleNet achieves state-of-the-art prediction accuracy in multiple domains including electricity, weather, and energy, while offering significant efficiency advantages by reducing over 90% of the required parameter quantity. Furthermore, as a novel plug-and-play technique, the RCF can also significantly improve the prediction accuracy of existing models, including PatchTST and iTransformer. The source code is available at: https://github.com/ACAT-SCUT/CycleNet.

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。