RECORD
Deep Epidemiological Modeling by Black-box Knowledge Distillation: An Accurate Deep Learning Model for COVID-19
Machine Learning · Submitted 20 Jan 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The case study on COVID-19 justifies that our approach accurately projects infections with much lower computation cost when observation data are limited.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | An accurate and efficient forecasting system is imperative to the prevention of emerging infectious diseases such as COVID-19 in public health. | background 1.00 | 0.04 | 0.03 | asserted 1.00 |
| s1 | This system requires accurate transient modeling, lower computation cost, and fewer observation data. | background 0.79 | 0.06 | 0.03 | asserted 1.00 |
| s2 | 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. | contribution 0.98 | 0.77 | 0.13 | asserted 0.97 |
| s3 | First, we leverage mixture models to develop an accurate, comprehensive, yet impractical simulation system. | method 0.95 | 0.89 | 0.03 | asserted 1.00 |
| s4 | Next, we use simulated observation sequences to query the simulation system to retrieve simulated projection sequences as knowledge. | method 1.00 | 0.92 | 0.03 | asserted 0.98 |
| s5 | Then, with the obtained query data, sequence mixup is proposed to improve query efficiency, increase knowledge diversity, and boost distillation model accuracy. | method 0.96 | 0.88 | 0.04 | asserted 0.98 |
| s6 | Finally, we train a student deep neural network with the retrieved and mixed observation-projection sequences for practical use. | method 0.99 | 0.94 | 0.08 | asserted 0.90 |
| s7 | The case study on COVID-19 justifies that our approach accurately projects infections with much lower computation cost when observation data are limited. | result 0.97 | 0.93 | 0.89 | asserted 0.98 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
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.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 9 sentences without a confident label
Compares with 1 paper
-
Next, we compare our student network with 7 state-of-the-art forecasting models reported from CDC [ref] .
Evaluating epidemic forecasts in an interval format · Competing Methods. · 0.90
Cites as background 1 paper
-
Knowledge distillation [ref] is widely used to solve deep neural network compression problem.
Distilling the Knowledge in a Neural Network · Knowledge Distillation · 0.93
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.