DyANE: Dynamics-aware node embedding for temporal networks

TL;DR

DyANE introduces a novel node embedding method tailored for temporal networks that captures dynamical process information, enabling improved prediction of epidemic spreading and system evolution from partial data.

Contribution

The paper presents DyANE, a dynamics-aware node embedding technique that leverages a modified supra-adjacency representation to predict dynamical processes in temporal networks.

Findings

Effective in predicting epidemic states in empirical networks

Enables nowcasting of infectious disease dynamics from partial observations

Outperforms traditional structure-focused embeddings in dynamical tasks

Abstract

Low-dimensional vector representations of network nodes have proven successful to feed graph data to machine learning algorithms and to improve performance across diverse tasks. Most of the embedding techniques, however, have been developed with the goal of achieving dense, low-dimensional encoding of network structure and patterns. Here, we present a node embedding technique aimed at providing low-dimensional feature vectors that are informative of dynamical processes occurring over temporal networks -- rather than of the network structure itself -- with the goal of enabling prediction tasks related to the evolution and outcome of these processes. We achieve this by using a modified supra-adjacency representation of temporal networks and building on standard embedding techniques for static graphs based on random-walks. We show that the resulting embedding vectors are useful for prediction tasks related to paradigmatic dynamical processes, namely epidemic spreading over empirical temporal networks. In particular, we illustrate the performance of our approach for the prediction of nodes' epidemic states in a single instance of a spreading process. We show how framing this task as a supervised multi-label classification task on the embedding vectors allows us to estimate the temporal evolution of the entire system from a partial sampling of nodes at random times, with potential impact for nowcasting infectious disease dynamics.