Optimising Network Efficiency in the Epidemic Scenario

10 Pages Posted: 16 Oct 2024

See all articles by Magdalena Proszewska

Magdalena Proszewska

University of Edinburgh

Michal Bujak

affiliation not provided to SSRN

Rafał Kucharski

Jagiellonian University in Krakow

Jacek Tabor

affiliation not provided to SSRN

Marek Smieja

affiliation not provided to SSRN

Abstract

We consider the problem of reducing virus spreading in the system network (graph) while keeping the utility of the whole system at the maximal level. To balance the above two opposite goals, we propose Deep Epidemic Efficiency Network (DEEN), an unsupervised clustering method, which optimises graph efficiency in an epidemic scenario using Graph Convolutional Neural Networks and a novel loss function. Given the desired virus transmission, it constructs a graph partition for which the predefined transmission rate is not exceeded and utility function is maximised. We show that proposed method successfully solves three real-life problems: ride-pooling service in New York City, economic exchange between regions in Poland, and information sharing via peer-to-peer network. In particular, by dividing 150 New York taxi travellers into four groups our method increases epidemic threshold more than twofold at the cost of reducing utility only by 13%.The model can be instrumental in future pandemic outbreaks when we need to balance between maintaining efficiency and preventing the spread of the virus.

Keywords: Graph neural networks, virus spread, Graph Clustering

Suggested Citation

Proszewska, Magdalena and Bujak, Michal and Kucharski, Rafał and Tabor, Jacek and Smieja, Marek, Optimising Network Efficiency in the Epidemic Scenario. Available at SSRN: https://ssrn.com/abstract=4976648 or http://dx.doi.org/10.2139/ssrn.4976648

Magdalena Proszewska (Contact Author)

University of Edinburgh ( email )

Old College
South Bridge
Edinburgh, EH8 9JY
United Kingdom

Michal Bujak

affiliation not provided to SSRN ( email )

No Address Available

Rafał Kucharski

Jagiellonian University in Krakow ( email )

Collegium Novum
ul. Gołębia 24
Kraków, 31-007
Poland

Jacek Tabor

affiliation not provided to SSRN ( email )

No Address Available

Marek Smieja

affiliation not provided to SSRN ( email )

No Address Available

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
24
Abstract Views
85
PlumX Metrics