Learning graph topology from metapopulation epidemic encoder-decoder
This addresses a persistent gap in modeling disease propagation for public health applications, though it appears incremental as it builds on existing inference methods.
The authors tackled the joint inference of epidemic parameters and mobility networks in metapopulation models, proposing encoder-decoder deep learning architectures that outperform state-of-the-art topology inference across diverse networks and show improved performance with additional pathogen data.
Metapopulation epidemic models are a valuable tool for studying large-scale outbreaks. With the limited availability of epidemic tracing data, it is challenging to infer the essential constituents of these models, namely, the epidemic parameters and the relevant mobility network between subpopulations. Either one of these constituents can be estimated while assuming the other; however, the problem of their joint inference has not yet been solved. Here, we propose two encoder-decoder deep learning architectures that infer metapopulation mobility graphs from time-series data, with and without the assumption of epidemic model parameters. Evaluation across diverse random and empirical mobility networks shows that the proposed approach outperforms the state-of-the-art topology inference. Further, we show that topology inference improves dramatically with data on additional pathogens. Our study establishes a robust framework for simultaneously inferring epidemic parameters and topology, addressing a persistent gap in modeling disease propagation.