A Predictive Approach To Enhance Time-Series Forecasting
This work improves forecasting accuracy for domains like healthcare and dynamical systems, but it appears incremental as it builds on existing predictive coding ideas.
The paper tackles the problem of time-series forecasting by addressing long-term dependencies and data distribution shifts, introducing Future-Guided Learning, which achieves a 44.8% increase in AUC-ROC for seizure prediction and a 23.4% reduction in MSE for nonlinear dynamical systems forecasting.
Accurate time-series forecasting is crucial in various scientific and industrial domains, yet deep learning models often struggle to capture long-term dependencies and adapt to data distribution shifts over time. We introduce Future-Guided Learning, an approach that enhances time-series event forecasting through a dynamic feedback mechanism inspired by predictive coding. Our method involves two models: a detection model that analyzes future data to identify critical events and a forecasting model that predicts these events based on current data. When discrepancies occur between the forecasting and detection models, a more significant update is applied to the forecasting model, effectively minimizing surprise, allowing the forecasting model to dynamically adjust its parameters. We validate our approach on a variety of tasks, demonstrating a 44.8% increase in AUC-ROC for seizure prediction using EEG data, and a 23.4% reduction in MSE for forecasting in nonlinear dynamical systems (outlier excluded).By incorporating a predictive feedback mechanism, Future-Guided Learning advances how deep learning is applied to time-series forecasting.