Estimating the state of epidemics spreading with graph neural networks

When an epidemic spreads into a population, it is often unpractical or impossible to have a continuous monitoring of all subjects involved. As an alternative, algorithmic solutions can be used to infer the state of the whole population from a limited amount of measures. We analyze the capability of deep neutral networks to solve this challenging task. Our proposed architecture is based on Graph Convolutional Neural Networks. As such it can reason on the effect of the underlying social network structure, which is recognized as the main component in the spreading of an epidemic. We test the proposed architecture with two scenarios modeled on the CoVid-19 pandemic: a generic homogeneous population, and a toy model of Boston metropolitan area.

[1]  Kilian Q. Weinberger,et al.  Feature hashing for large scale multitask learning , 2009, ICML '09.

[2]  Umberto Spagnolini,et al.  Consensus-Based Algorithms for Distributed Network-State Estimation and Localization , 2017, IEEE Transactions on Signal and Information Processing over Networks.

[3]  Giorgio Battistelli,et al.  Data-driven communication for state estimation with sensor networks , 2012, Autom..

[4]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[5]  J. Nathan Kutz,et al.  Deep learning in fluid dynamics , 2017, Journal of Fluid Mechanics.

[6]  G. Chowell,et al.  Transmission potential and severity of COVID-19 in South Korea , 2020, International Journal of Infectious Diseases.

[7]  Tamás Péni,et al.  Nonlinear model predictive control with logic constraints for COVID-19 management , 2020, Nonlinear dynamics.

[8]  Luyang Liu,et al.  Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks , 2020, ArXiv.

[9]  Derui Ding,et al.  Distributed recursive filtering for stochastic systems under uniform quantizations and deception attacks through sensor networks , 2017, Autom..

[10]  Zidong Wang,et al.  Synchronization and State Estimation for Discrete-Time Complex Networks With Distributed Delays , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  Santiago Segarra,et al.  Deep Demixing: Reconstructing the Evolution of Epidemics using Graph Neural Networks , 2020, 2021 29th European Signal Processing Conference (EUSIPCO).

[12]  M. Peirlinck,et al.  Outbreak dynamics of COVID-19 in Europe and the effect of travel restrictions , 2020, medRxiv.

[13]  Raymond C Browning,et al.  Exploiting Social Networks to Mitigate the Obesity Epidemic , 2009, Obesity.

[14]  Davide Bacciu,et al.  A Gentle Introduction to Deep Learning for Graphs , 2019, Neural Networks.

[15]  Lucie Abeler-Dörner,et al.  Quantifying SARS-CoV-2 transmission suggests epidemic control with digital contact tracing , 2020, Science.

[16]  Isabel J. Raabe,et al.  Social network-based distancing strategies to flatten the COVID-19 curve in a post-lockdown world , 2020, Nature Human Behaviour.

[17]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[18]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[19]  Wei Wang,et al.  Coevolution spreading in complex networks , 2019, Physics Reports.

[20]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[21]  Shuicheng Yan,et al.  Semantic Object Parsing with Graph LSTM , 2016, ECCV.

[22]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[23]  A. Hill,et al.  Dynamics of COVID-19 under social distancing measures are driven by transmission network structure , 2020, medRxiv.

[24]  Daniel W. C. Ho,et al.  State estimation for delayed neural networks , 2005, IEEE Transactions on Neural Networks.

[25]  Qing-Long Han,et al.  A Survey on Model-Based Distributed Control and Filtering for Industrial Cyber-Physical Systems , 2019, IEEE Transactions on Industrial Informatics.

[26]  Piet Van Mieghem,et al.  Epidemic processes in complex networks , 2014, ArXiv.

[27]  Alessandro Vespignani,et al.  Real-time numerical forecast of global epidemic spreading: case study of 2009 A/H1N1pdm , 2012, BMC Medicine.

[28]  R. Sarkar,et al.  GraphCovidNet: A graph neural network based model for detecting COVID-19 from CT scans and X-rays of chest , 2021, Scientific Reports.

[29]  Steven L. Brunton,et al.  Deep learning for universal linear embeddings of nonlinear dynamics , 2017, Nature Communications.

[30]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[31]  Alessandro Vespignani,et al.  Finding Patient Zero: Learning Contagion Source with Graph Neural Networks , 2020, ArXiv.

[32]  Zidong Wang,et al.  On Kalman-Consensus Filtering With Random Link Failures Over Sensor Networks , 2018, IEEE Transactions on Automatic Control.

[33]  Cosimo Della Santina,et al.  Covid-19 and Flattening the Curve: a Feedback Control Perspective , 2021, 2021 American Control Conference (ACC).

[34]  D. Gillespie.  Exact Stochastic Simulation of Coupled Chemical Reactions , 1977 .

[35]  Jimeng Sun,et al.  STAN: Spatio-Temporal Attention Network for Pandemic Prediction Using Real World Evidence. , 2020, ArXiv.

[36]  Emilio Zagheni,et al.  What types of contacts are important for the spread of infections?: using contact survey data to explore European mixing patterns. , 2011, Epidemics.

[37]  Peng Shi,et al.  Robust Estimation for Neural Networks With Randomly Occurring Distributed Delays and Markovian Jump Coupling , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[38]  Tom Britton,et al.  Stochastic Epidemic Models with Inference , 2019, Lecture Notes in Mathematics.

[39]  W. Liang,et al.  Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions , 2020, Journal of thoracic disease.

[40]  D. Rus,et al.  Covid-19 and Flattening the Curve: A Feedback Control Perspective , 2021, IEEE Control Systems Letters.

[41]  Kathryn B. Laskey,et al.  Stochastic blockmodels: First steps , 1983 .

[42]  Estimating the state of epidemics spreading with graph neural networks , 2022, Nonlinear dynamics.

[43]  J. A. M. Valle.  Predicting the number of total COVID-19 cases and deaths in Brazil by the Gompertz model , 2020, Nonlinear Dynamics.

[44]  Shaobo He,et al.  SEIR modeling of the COVID-19 and its dynamics , 2020, Nonlinear Dynamics.

[45]  Cheng-Wei Fei,et al.  Multi-extremum-modified response basis model for nonlinear response prediction of dynamic turbine blisk , 2021, Engineering with Computers.

[46]  Dan Zhang,et al.  Asynchronous State Estimation for Discrete-Time Switched Complex Networks With Communication Constraints , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[47]  Santiago Segarra,et al.  Network Topology Inference from Spectral Templates , 2016, IEEE Transactions on Signal and Information Processing over Networks.

[48]  Vito Latora,et al.  Simplicial models of social contagion , 2018, Nature Communications.

[49]  Peter Stone,et al.  Reinforcement Learning for Optimization of COVID-19 Mitigation policies , 2020, ArXiv.

[50]  Georgios B. Giannakis,et al.  Topology Identification and Learning over Graphs: Accounting for Nonlinearities and Dynamics , 2018, Proceedings of the IEEE.

[51]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[52]  Seattle,et al.  Inferring high-resolution human mixing patterns for disease modeling , 2020, Nature communications.

[53]  Hsien-Ho Lin,et al.  Contact Tracing Assessment of COVID-19 Transmission Dynamics in Taiwan and Risk at Different Exposure Periods Before and After Symptom Onset , 2020, JAMA internal medicine.

[54]  Thomas Peters,et al.  Data-driven science and engineering: machine learning, dynamical systems, and control , 2019, Contemporary Physics.

[55]  Giorgio Battistelli,et al.  Stability of consensus extended Kalman filter for distributed state estimation , 2016, Autom..