Deep Imbalanced Time-series Forecasting via Local Discrepancy Density
This addresses forecasting accuracy issues for domains with rare events, but it is incremental as it builds on existing models with a reweighting technique.
The paper tackles the problem of abrupt changes in time-series forecasting, which act as noisy samples and hinder learning of generalizable patterns, by proposing a reweighting framework that down-weights losses from abrupt changes and up-weights normal states, reducing MSE by 10.1% on average and up to 18.6% in SOTA models.
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.