Estimating Infection Sources in a Network with Incomplete Observations

We consider the problem of estimating infection sources based on incomplete observations of the set of infected nodes at some point in time, assuming that the infection spreading process follows an Susceptible-Infected (SI) model. We derive an estimator that finds the source nodes associated with the most likely infection path that yields the incomplete observations. Moreover, we design a heuristic algorithm to find the proposed estimator. Simulation results on geometric trees suggest that our estimator performs consistently better than the minimum distance centrality based heuristic.