A Bayesian generative neural network framework for epidemic inference problems

Abstract

The reconstruction of missing information in epidemic spreading on contact networks can be essential in the prevention and containment strategies. The identification and warning of infectious but asymptomatic individuals (i.e., contact tracing), the well-known patient-zero problem, or the inference of the infectivity values in structured populations are examples of significant epidemic inference problems. As the number of possible epidemic cascades grows exponentially with the number of individuals involved and only an almost negligible subset of them is compatible with the observations (e.g., medical tests), epidemic inference in contact networks poses incredible computational challenges. We present a new generative neural networks framework that learns to generate the most probable infection cascades compatible with observations. The proposed method achieves better (in some cases, significantly better) or comparable results with existing methods in all problems considered both in synthetic and real contact networks. Given its generality, clear Bayesian and variational nature, the presented framework paves the way to solve fundamental inference epidemic problems with high precision in small and medium-sized real case scenarios such as the spread of infections in workplaces and hospitals.

arXiv comment30 pages, 6 figures, 1 table

References in corpus (19)

• Epidemic processes in complex networks
• Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
• Multiscale mobility networks and the large scale spreading of infectious diseases
• Contact patterns in a high school: a comparison between data collected using wearable sensors, contact diaries and friendship surveys
• Inferring the origin of an epidemic with a dynamic message-passing algorithm
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Can co-location be used as a proxy for face-to-face contacts?
• Bayesian inference of epidemics on networks via Belief Propagation
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Containing epidemic outbreaks by message-passing techniques
• Neural network based country wise risk prediction of COVID-19
• Efficient generative modeling of protein sequences using simple autoregressive models
• Identification of Patient Zero in Static and Temporal Networks - Robustness and Limitations
• Variational Neural Annealing
• Optimizing spread dynamics on graphs by message passing
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Epidemic mitigation by statistical inference from contact tracing data
• Network reconstruction from infection cascades
• Solving Statistical Mechanics on Sparse Graphs with Feedback Set Variational Autoregressive Networks

Cited by in corpus (7)

• New Trends on the Systems Approach to Modeling SARS-CoV-2 Pandemics in a Globally Connected Planet
• The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
• Bayes-optimal inference for spreading processes on random networks
• Sparse Autoregressive Neural Networks for Classical Spin Systems
• Inference in conditioned dynamics through causality restoration
• Statistical Mechanics of Inference in Epidemic Spreading
• Small-Coupling Dynamic Cavity: a Bayesian mean-field framework for epidemic inference