DyANE: Dynamics-aware node embedding for temporal networks

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.

arXiv commentupdated version with additional results

References in corpus (19)

• Scikit-learn: Machine Learning in Python
• Statistical mechanics of complex networks
• The structure and function of complex networks
• Statistical physics of social dynamics
• Epidemic processes in complex networks
• Multilayer Networks
• Temporal Networks
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Diffusion dynamics on multiplex networks
• Dynamics of person-to-person interactions from distributed RFID sensor networks
• High resolution dynamical mapping of social interactions with active RFID
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• DynGEM: Deep Embedding Method for Dynamic Graphs
• Betweenness Preference: Quantifying Correlations in the Topological Dynamics of Temporal Networks
• Epidemiologically optimal static networks from temporal network data
• Efficient limited-time reachability estimation in temporal networks
• Reconstructing a cascade from temporal observations
• Network Infusion to Infer Information Sources in Networks
• Collaborative Inference of Coexisting Information Diffusions

Cited by in corpus (2)

• Representation Learning for Dynamic Graphs: A Survey
• weg2vec: Event embedding for temporal networks