Deep learning of contagion dynamics on complex networks

TL;DR

This paper introduces a deep learning approach using graph neural networks to model and predict contagion dynamics on complex networks, overcoming limitations of traditional mechanistic models and enabling analysis on real-world data.

Contribution

The authors develop a graph neural network framework that learns local contagion mechanisms directly from data, with minimal assumptions, applicable to various complex network structures.

Findings

Accurately models diverse contagion dynamics

Enables simulations on arbitrary network structures

Successfully applied to COVID-19 outbreak data in Spain

Abstract

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.