Article Dans Une Revue Nature Communications Année : 2025

A predictive approach to enhance time-series forecasting

Résumé

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.

Fichier principal
Vignette du fichier
s41467-025-63786-4.pdf (946.72 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05293576 , version 1 (14-03-2026)

Licence

Identifiants

Citer

Skye Gunasekaran, Assel Kembay, Hugo Ladret, Rui-Jie Zhu, Laurent U Perrinet, et al.. A predictive approach to enhance time-series forecasting. Nature Communications, 2025, 16 (1), pp.8645. ⟨10.1038/s41467-025-63786-4⟩. ⟨hal-05293576⟩
154 Consultations
45 Téléchargements

Altmetric

Partager

  • More