Search papers, labs, and topics across Lattice.
The paper introduces DynaME, a hybrid framework for online time series forecasting that addresses concept drift by distinguishing between Recurring and Emergent drift types. DynaME uses a committee of specialized experts dynamically fitted to historical periodic patterns for Recurring Drift, and switches to a stable, general expert when high uncertainty indicates Emergent Drift. Experiments on benchmark datasets show DynaME outperforms existing baselines by effectively adapting to both types of concept drift.
Stop treating concept drift as one thing: DynaME's hybrid approach, separating recurring and emergent drifts, unlocks better online time series forecasting.
Online Time Series Forecasting (OTSF) requires models to continuously adapt to concept drift. However, existing methods often treat concept drift as a monolithic phenomenon. To address this limitation, we first redefine concept drift by categorizing it into two distinct types: Recurring Drift, where previously seen patterns reappear, and Emergent Drift, where entirely new patterns emerge. We then propose DynaME (Dynamic Multi-period Experts), a novel hybrid framework designed to effectively address this dual nature of drift. For Recurring Drift, DynaME employs a committee of specialized experts that are dynamically fitted to the most relevant historical periodic patterns at each time step. For Emergent Drift, the framework detects high-uncertainty scenarios and shifts reliance to a stable, general expert. Extensive experiments on several benchmark datasets and backbones demonstrate that DynaME effectively adapts to both concept drifts and significantly outperforms existing baselines.
