Inferring the origin of an epidemic with a dynamic message-passing algorithm

TL;DR

This paper introduces a dynamic message-passing algorithm to accurately identify the origin of an epidemic outbreak from partial network data, improving upon existing methods in efficiency and accuracy.

Contribution

The paper presents a novel inference algorithm based on dynamic message-passing equations for epidemic source detection, effective even with partial node information.

Findings

Significant performance improvement over existing methods

Effective with partial node state information

Maintains efficiency on large contact networks

Abstract

We study the problem of estimating the origin of an epidemic outbreak -- given a contact network and a snapshot of epidemic spread at a certain time, determine the infection source. Finding the source is important in different contexts of computer or social networks. We assume that the epidemic spread follows the most commonly used susceptible-infected-recovered model. We introduce an inference algorithm based on dynamic message-passing equations, and we show that it leads to significant improvement of performance compared to existing approaches. Importantly, this algorithm remains efficient in the case where one knows the state of only a fraction of nodes.