Learning graph topology from metapopulation epidemic encoder-decoder

TL;DR

This paper introduces deep learning models that jointly infer epidemic parameters and mobility networks from outbreak data, significantly improving accuracy over existing methods and addressing a key challenge in epidemic modeling.

Contribution

The authors develop two encoder-decoder architectures capable of inferring mobility graphs and epidemic parameters simultaneously from time-series data.

Findings

Outperforms state-of-the-art topology inference methods.

Inference accuracy improves with additional pathogen data.

Robust framework applicable to diverse networks.

Abstract

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.