Model-Attentive Ensemble Learning for Sequence Modeling
This work addresses the problem of adapting to time-varying distributions in medical time-series data for healthcare applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled the challenge of temporal conditional shift in medical time-series prediction by introducing MAES, a model-attentive ensemble learning method, which significantly outperformed popular sequence models on datasets with temporal shift.
Medical time-series datasets have unique characteristics that make prediction tasks challenging. Most notably, patient trajectories often contain longitudinal variations in their input-output relationships, generally referred to as temporal conditional shift. Designing sequence models capable of adapting to such time-varying distributions remains a prevailing problem. To address this we present Model-Attentive Ensemble learning for Sequence modeling (MAES). MAES is a mixture of time-series experts which leverages an attention-based gating mechanism to specialize the experts on different sequence dynamics and adaptively weight their predictions. We demonstrate that MAES significantly out-performs popular sequence models on datasets subject to temporal shift.