Event Graphs: Advances and Applications of Second-Order Time-Unfolded Temporal Network Models

TL;DR

This paper introduces event graphs, a second-order time-unfolded model for temporal networks, enabling detailed analysis of higher-order structures and non-dyadic interactions in real-time data.

Contribution

It presents a generalized framework for modeling temporal networks with event graphs, capturing complex temporal and higher-order interactions beyond static or aggregated models.

Findings

Event graphs reveal higher-order topological-temporal structures.

The framework extends to hyper-events, non-dyadic interactions.

Analysis captures properties unobserved in static models.

Abstract

Recent advances in data collection and storage have allowed both researchers and industry alike to collect data in real time. Much of this data comes in the form of 'events', or timestamped interactions, such as email and social media posts, website clickstreams, or protein-protein interactions. This of type data poses new challenges for modelling, especially if we wish to preserve all temporal features and structure. We propose a generalised framework to explore temporal networks using second-order time-unfolded models, called event graphs. Through examples we demonstrate how event graphs can be used to understand the higher-order topological-temporal structure of temporal networks and capture properties of the network that are unobserved when considering either a static (or time-aggregated) model. Furthermore, we show that by modelling a temporal network as an event graph our analysis extends easily to consider non-dyadic interactions, known as hyper-events.