Latent Self-Exciting Point Process Model for Spatial-Temporal Networks

Abstract

We propose a latent self-exciting point process model that describes geographically distributed interactions between pairs of entities. In contrast to most existing approaches that assume fully observable interactions, here we consider a scenario where certain interaction events lack information about participants. Instead, this information needs to be inferred from the available observations. We develop an efficient approximate algorithm based on variational expectation-maximization to infer unknown participants in an event given the location and the time of the event. We validate the model on synthetic as well as real-world data, and obtain very promising results on the identity-inference task. We also use our model to predict the timing and participants of future events, and demonstrate that it compares favorably with baseline approaches.

20 pages, 6 figures (v3); 11 pages, 6 figures (v2); previous version appeared in the 9th Bayesian Modeling Applications Workshop, UAI'12

References in corpus (6)

• Missing and spurious interactions and the reconstruction of complex networks
• Dynamical and bursty interactions in social networks
• Modeling Information Propagation with Survival Theory
• Self-exciting hurdle models for terrorist activity
• Modeling Events with Cascades of Poisson Processes
• Learning Continuous-Time Social Network Dynamics

Cited by in corpus (12)

• Modern temporal network theory: A colloquium
• Clustering implies geometry in networks
• Hidden Markov models for the activity profile of terrorist groups
• Universal Components of Real-world Diffusion Dynamics based on Point Processes
• Modeling of Spatio-Temporal Hawkes Processes with Randomized Kernels
• Spatio-Temporal Modeling of Users' Check-ins in Location-Based Social Networks
• A semiparametric extension of the stochastic block model for longitudinal networks
• Understanding the Predictive Power of Computational Mechanics and Echo State Networks in Social Media
• Multivariate Spatiotemporal Hawkes Processes and Network Reconstruction
• A survey on modelling of infectious disease spread and control on social contact networks
• Diffusion on dynamic contact networks with indirect transmission links
• A Metric Space for Point Process Excitations