A Graph Regularized Point Process Model For Event Propagation Sequence

TL;DR

This paper introduces a Graph Regularized Point Process model that captures latent graph structures and event dynamics for better interpretability and prediction of event propagation sequences.

Contribution

The paper proposes a novel GRPP model combining graph propagation and temporal attention, enhancing interpretability and predictive performance over existing methods.

Findings

Outperforms existing models in propagation time prediction

Achieves higher accuracy in node prediction tasks

Provides interpretable influence strengths between nodes

Abstract

Point process is the dominant paradigm for modeling event sequences occurring at irregular intervals. In this paper we aim at modeling latent dynamics of event propagation in graph, where the event sequence propagates in a directed weighted graph whose nodes represent event marks (e.g., event types). Most existing works have only considered encoding sequential event history into event representation and ignored the information from the latent graph structure. Besides they also suffer from poor model explainability, i.e., failing to uncover causal influence across a wide variety of nodes. To address these problems, we propose a Graph Regularized Point Process (GRPP) that can be decomposed into: 1) a graph propagation model that characterizes the event interactions across nodes with neighbors and inductively learns node representations; 2) a temporal attentive intensity model, whose excitation and time decay factors of past events on the current event are constructed via the contextualization of the node embedding. Moreover, by applying a graph regularization method, GRPP provides model interpretability by uncovering influence strengths between nodes. Numerical experiments on various datasets show that GRPP outperforms existing models on both the propagation time and node prediction by notable margins.