Deep Epidemiological Modeling by Black-box Knowledge Distillation: An Accurate Deep Learning Model for COVID-19
This work addresses the problem of predicting infectious disease outbreaks like COVID-19 for public health, but it is incremental as it builds on existing knowledge distillation and simulation methods.
The paper tackled the challenge of accurate and efficient COVID-19 forecasting by proposing a deep learning approach using black-box knowledge distillation, which achieved accurate infection projections with much lower computation cost and limited observation data.
An accurate and efficient forecasting system is imperative to the prevention of emerging infectious diseases such as COVID-19 in public health. This system requires accurate transient modeling, lower computation cost, and fewer observation data. To tackle these three challenges, we propose a novel deep learning approach using black-box knowledge distillation for both accurate and efficient transmission dynamics prediction in a practical manner. First, we leverage mixture models to develop an accurate, comprehensive, yet impractical simulation system. Next, we use simulated observation sequences to query the simulation system to retrieve simulated projection sequences as knowledge. Then, with the obtained query data, sequence mixup is proposed to improve query efficiency, increase knowledge diversity, and boost distillation model accuracy. Finally, we train a student deep neural network with the retrieved and mixed observation-projection sequences for practical use. The case study on COVID-19 justifies that our approach accurately projects infections with much lower computation cost when observation data are limited.