Transfer Graph Neural Networks for Pandemic Forecasting

TL;DR

This paper introduces a transfer graph neural network approach for COVID-19 forecasting that leverages human mobility data and meta-learning to improve prediction accuracy across different countries.

Contribution

It presents a novel combination of graph neural networks and model-agnostic meta-learning for pandemic forecasting, addressing data scarcity and cross-country transferability.

Findings

GNNs outperform traditional forecasting methods in COVID-19 case prediction.

Transfer learning significantly improves model accuracy for secondary waves.

The approach effectively captures mobility-driven diffusion patterns.

Abstract

The recent outbreak of COVID-19 has affected millions of individuals around the world and has posed a significant challenge to global healthcare. From the early days of the pandemic, it became clear that it is highly contagious and that human mobility contributes significantly to its spread. In this paper, we study the impact of population movement on the spread of COVID-19, and we capitalize on recent advances in the field of representation learning on graphs to capture the underlying dynamics. Specifically, we create a graph where nodes correspond to a country's regions and the edge weights denote human mobility from one region to another. Then, we employ graph neural networks to predict the number of future cases, encoding the underlying diffusion patterns that govern the spread into our learning model. Furthermore, to account for the limited amount of training data, we capitalize on the pandemic's asynchronous outbreaks across countries and use a model-agnostic meta-learning based method to transfer knowledge from one country's model to another's. We compare the proposed approach against simple baselines and more traditional forecasting techniques in 3 European countries. Experimental results demonstrate the superiority of our method, highlighting the usefulness of GNNs in epidemiological prediction. Transfer learning provides the best model, highlighting its potential to improve the accuracy of the predictions in case of secondary waves, if data from past/parallel outbreaks is utilized.