Time-series forecasting models often encounter abrupt changes in a given period of time which generally occur due to unexpected or unknown events. Despite their scarce occurrences in the training set, abrupt changes incur loss that significantly contributes to the total loss. Therefore, they act as noisy training samples and prevent the model from learning generalizable patterns, namely the normal states. Based on our findings, we propose a reweighting framework that down-weights the losses incurred by abrupt changes and up-weights those by normal states. For the reweighting framework, we first define a measurement termed Local Discrepancy (LD) which measures the degree of abruptness of a change in a given period of time. Since a training set is mostly composed of normal states, we then consider how frequently the temporal changes appear in the training set based on LD. Our reweighting framework is applicable to existing time-series forecasting models regardless of the architectures. Through extensive experiments on 12 time-series forecasting models over eight datasets with various in-output sequence lengths, we demonstrate that applying our reweighting framework reduces MSE by 10.1% on average and by up to 18.6% in the state-of-the-art model.

翻译：时间序列预测模型常常会遇到给定时间段内的突变情况，这些突变通常由不可预见或未知事件引发。尽管突变在训练集中出现频率较低，但其产生的损失却对总损失有显著贡献。因此，它们充当了噪声训练样本，阻碍模型学习可泛化的模式，即正常状态。基于我们的发现，我们提出了一种重新加权框架，该框架降低突变引发的损失权重，并提高正常状态损失的权重。在该重新加权框架中，我们首先定义了一种称为局部差异的度量，该度量衡量给定时间段内变化的突变程度。由于训练集主要由正常状态组成，我们随后基于局部差异考虑时间变化在训练集中出现的频率。我们的重新加权框架适用于现有时间序列预测模型，且不受其架构限制。通过在8个数据集上对12种时间序列预测模型进行广泛实验（涵盖不同输入输出序列长度），我们证明应用该重新加权框架可使均方误差平均降低10.1%，在最新模型中最高降低18.6%。