Finding Patient Zero: Learning Contagion Source with Graph Neural Networks

TL;DR

This paper introduces a graph neural network approach to accurately and efficiently identify the initial source of an epidemic, outperforming traditional methods and providing theoretical insights into the limits of source detection.

Contribution

The paper presents a novel GNN-based method for locating epidemic sources, establishing theoretical bounds and demonstrating superior speed and accuracy over existing techniques.

Findings

GNNs can identify P0 close to the theoretical accuracy bound

GNN inference is over 100 times faster than classic methods

Early contact-tracing is crucial as epidemic detection becomes impossible after a certain time

Abstract

Locating the source of an epidemic, or patient zero (P0), can provide critical insights into the infection's transmission course and allow efficient resource allocation. Existing methods use graph-theoretic centrality measures and expensive message-passing algorithms, requiring knowledge of the underlying dynamics and its parameters. In this paper, we revisit this problem using graph neural networks (GNNs) to learn P0. We establish a theoretical limit for the identification of P0 in a class of epidemic models. We evaluate our method against different epidemic models on both synthetic and a real-world contact network considering a disease with history and characteristics of COVID-19. % We observe that GNNs can identify P0 close to the theoretical bound on accuracy, without explicit input of dynamics or its parameters. In addition, GNN is over 100 times faster than classic methods for inference on arbitrary graph topologies. Our theoretical bound also shows that the epidemic is like a ticking clock, emphasizing the importance of early contact-tracing. We find a maximum time after which accurate recovery of the source becomes impossible, regardless of the algorithm used.