• Corpus ID: 243833059

Epidemic inference through generative neural networks

  title={Epidemic inference through generative neural networks},
  author={Indaco Biazzo and Alfredo Braunstein and Luca Dall’Asta and Fabio Mazza},
Reconstructing missing information in epidemic spreading on contact networks can be essential in prevention and containment strategies. For instance, identifying and warning infective but asymptomatic individuals (e.g., manual contact tracing) helped contain outbreaks in the COVID-19 pandemic. The number of possible epidemic cascades typically grows exponentially with the number of individuals involved. The challenge posed by inference problems in the epidemics processes originates from the… 

Figures and Tables from this paper


Estimating the state of epidemics spreading with graph neural networks
The capability of deep neural networks to solve the challenge of spreading an epidemic by using algorithmic solutions that can infer the state of the whole population from a limited number of measures is analyzed.
Finding Patient Zero: Learning Contagion Source with Graph Neural Networks
A theoretical limit is established for the identification of P0 in a class of epidemic models using graph neural networks to learn P0, showing that the epidemic is like a ticking clock, emphasizing the importance of early contact-tracing.
Bayesian inference of epidemics on networks via Belief Propagation
Numerical simulations show that the method based on the belief propagation algorithm is efficient, naturally distributed, and exact on trees, and outperforms previous ones on both synthetic and real networks.
Network reconstruction from infection cascades
It is shown that it is possible to reconstruct the whole structure of an interaction network and to simultaneously infer the complete time course of activation spreading, relying just on single epoch (i.e. snapshot) or time-scattered observations of a small number of activity cascades.
Identification of Patient Zero in Static and Temporal Networks: Robustness and Limitations.
The statistical inference problem of detecting the source of epidemics from a snapshot of spreading on an arbitrary network structure is studied and the detectability limits for the susceptible-infected-recovered model, which primarily depend on the spreading process characteristics are demonstrated.
Epidemic mitigation by statistical inference from contact tracing data
This work aims to quantify the epidemiological gain one would obtain if, additionally, individuals who were recently in contact could exchange messages of information and proposes to use probabilistic risk estimation to optimize testing and quarantining strategies for the control of an epidemic.
Inferring the origin of an epidemy with dynamic message-passing algorithm
An inference algorithm based on dynamic message-passing equations is introduced and it is shown that it leads to significant improvement of performance compared to existing approaches, and remains efficient in the case where the snapshot sees only a part of the network.
Neural network based country wise risk prediction of COVID-19
A shallow long short-term memory (LSTM) based neural network to predict the risk category of a country and shows that the proposed pipeline outperforms state-of-the-art methods for data of 180 countries and can be a useful tool for such risk categorization.
Modelling disease outbreaks in realistic urban social networks
The results suggest that outbreaks can be contained by a strategy of targeted vaccination combined with early detection without resorting to mass vaccination of a population.