Node-embedding methods for temporal networks in the context of epidemiology

In this task, we will explore node-embedding methods aimed at exposing in the low-dimensional space structural features and relevant patterns of the network that are not necessarily evident in the network representation [75]. In the context of specific dynamical process such as epidemic spread over temporal networks – in which network nodes exist in few discrete states and the dynamics consists of transitions between such states (e.g., a “susceptible” node becoming “infectious”) – we will focus on the task of predicting the nodes’ states over time for a single realization of the epidemic process in a multi-label classification setting. This goal might have important implications such as for example estimating the temporal evolution of the entire system from sparse observations, consistently across several data sets and across a broad range of parameters of an epidemic model.