Deep learning of contagion dynamics on complex networks
This work addresses the challenge of improving quantitative predictions for contagion dynamics, such as disease spread, for researchers and policymakers, but it is incremental as it builds on existing deep learning methods.
The authors tackled the problem of forecasting contagion dynamics on complex networks, where traditional mechanistic models are limited by simplifying assumptions, and proposed a deep learning approach using graph neural networks to learn effective local mechanisms from time series data, demonstrating its accuracy on various contagion dynamics and applying it to real COVID-19 outbreak data in Spain.
Forecasting the evolution of contagion dynamics is still an open problem to which mechanistic models only offer a partial answer. To remain mathematically or computationally tractable, these models must rely on simplifying assumptions, thereby limiting the quantitative accuracy of their predictions and the complexity of the dynamics they can model. Here, we propose a complementary approach based on deep learning where the effective local mechanisms governing a dynamic on a network are learned from time series data. Our graph neural network architecture makes very few assumptions about the dynamics, and we demonstrate its accuracy using different contagion dynamics of increasing complexity. By allowing simulations on arbitrary network structures, our approach makes it possible to explore the properties of the learned dynamics beyond the training data. Finally, we illustrate the applicability of our approach using real data of the COVID-19 outbreak in Spain. Our results demonstrate how deep learning offers a new and complementary perspective to build effective models of contagion dynamics on networks.