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

TL;DR

This paper introduces a latent self-exciting point process model for spatial-temporal networks that infers missing participant information and predicts future interactions, validated on synthetic and real data.

Contribution

It presents a novel model and an efficient variational EM algorithm to infer unobserved participants in spatial-temporal interactions.

Findings

Accurately infers unknown participants in events.

Predicts future event timing and participants effectively.

Outperforms baseline methods in identity inference and prediction.

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.