weg2vec: Event embedding for temporal networks

Abstract

Network embedding techniques are powerful to capture structural regularities in networks and to identify similarities between their local fabrics. However, conventional network embedding models are developed for static structures, commonly consider nodes only and they are seriously challenged when the network is varying in time. Temporal networks may provide an advantage in the description of real systems, but they code more complex information, which could be effectively represented only by a handful of methods so far. Here, we propose a new method of event embedding of temporal networks, called weg2vec, which builds on temporal and structural similarities of events to learn a low dimensional representation of a temporal network. This projection successfully captures latent structures and similarities between events involving different nodes at different times and provides ways to predict the final outcome of spreading processes unfolding on the temporal structure.

References in corpus (21)

• Statistical mechanics of complex networks
• The structure and function of complex networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• The origin of bursts and heavy tails in human dynamics
• Link communities reveal multiscale complexity in networks
• Higher-order organization of complex networks
• Dynamics of person-to-person interactions from distributed RFID sensor networks
• High resolution dynamical mapping of social interactions with active RFID
• Activity driven modeling of time varying networks
• Small But Slow World: How Network Topology and Burstiness Slow Down Spreading
• Line Graphs, Link Partitions and Overlapping Communities
• Time varying networks and the weakness of strong ties
• Causality-Driven Slow-Down and Speed-Up of Diffusion in Non-Markovian Temporal Networks
• Detecting the community structure and activity patterns of temporal networks: a non-negative tensor factorization approach
• Topological strata of weighted complex networks
• Diffusion on networked systems is a question of time or structure
• Randomized reference models for temporal networks
• From calls to communities: a model for time varying social networks
• Activity clocks: spreading dynamics on temporal networks of human contact
• DyANE: Dynamics-aware node embedding for temporal networks