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.
Highlights
Network embedding techniques are powerful to capture structural regularities in networks and to identify similarities between their local fabrics
An embedding method of temporal networks may take a list of temporal interactions as input, and provide a lower dimensional representation, in which vectors corresponding to similar nodes or events in the original structure ideally point close to each other in the embedding
Embedding of networks has recently drawn a lot of attention as it both provides lower dimensional representations of networks and proves to be efficient to resolve task such as link prediction, node classification or anomaly detection
Summary
Network embedding techniques are powerful to capture structural regularities in networks and to identify similarities between their local fabrics. This is an event embedding method, which represents an entire temporal network in the same reduced dimensional abstract space It is based on combined event contexts built by sampling locally a higher-order static representation of temporal networks, which in turn code the complex patterns characterising the structure and dynamics of real world networks. This is an unsupervised representation learning technique, which can consider the past and future context of an event simultaneously. In the final Sections, we present the discussion of the results and the analysis of the methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
