arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.15869cs.LGcs.AI
收藏

面向长时间序列预测的长输入序列网络

Long Input Sequence Network for Long Time Series Forecasting

Chao Ma, Yikai Hou, Xiang Li, Yinggang Sun, Haining Yu

AI总结:

针对长时间序列预测中延长输入易过拟合的问题,提出解耦多尺度时间模式的思路,设计MPSD模块与MTPR网络,支持10倍长输入,实现38%最大精度提升,同时降低复杂度并提升可解释性。

摘要:

固定长度的短输入是深度学习方法在长时间序列预测任务中的主要瓶颈。延长输入长度会导致过拟合,使准确率迅速下降。我们的研究表明,这种过拟合是时间序列中的多尺度模式耦合与当前模型固定聚焦尺度共同作用的结果。首先,我们发现时间序列在不同尺度下呈现的模式反映了其多周期特性,每个尺度对应特定的周期长度。其次,我们发现token(令牌)大小主导着模型行为,因为它决定了模型聚焦的尺度以及可容纳的上下文规模。我们的思路是解耦时间序列的多尺度时间模式,并以每个模式对应的周期长度作为token大小对其进行建模。我们提出了一种新型序列分解模块MPSD(多周期尺度分解),以及多令牌模式识别神经网络MTPR,使模型能够处理最长达10倍长度的输入。充足的上下文提升了模型性能(最大精度提升38%),且该解耦方法具备低复杂度(成本为原有方法的0.22倍)和高可解释性的优势。

英文摘要:

Short fixed-length inputs are the main bottleneck of deep learning methods in long time-series forecasting tasks. Prolonging input length causes overfitting, rapidly deteriorating accuracy. Our research indicates that the overfitting is a combination reaction of the multi-scale pattern coupling in time series and the fixed focusing scale of current models. First, we find that the patterns exhibited by a time series across various scales are reflective of its multi-periodic nature, where each scale corresponds to specific period length. Second, We find that the token size predominantly dictates model behavior, as it determines the scale at which the model focuses and the context size it can accommodate. Our idea is to decouple the multi-scale temporal patterns of time series and to model each pattern with its corresponding period length as token size. We introduced a novel series-decomposition module(MPSD), and a Multi-Token Pattern Recognition neural network(MTPR), enabling the model to handle \textit{inputs up to $10\times$ longer}. Sufficient context enhances performance(\textit{38% maximum precision improvement}), and the decoupling approach offers \textit{Low complexity($0.22\times$ cost)} and \textit{high interpretability}.

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。

↑