Model-Attentive Ensemble Learning for Sequence Modeling

• Published in: arXiv.org
• Main Authors: Bourgin, Victor D, Bica, Ioana, van der Schaar, Mihaela
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 23.02.2021
• Subjects: Datasets; Modelling; Series (mathematics)
• ISSN: 2331-8422

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.