Variational Neural Temporal Point Process

TL;DR

This paper introduces VNTPP, a variational neural network model for temporal point processes that improves event type and timing predictions by modeling latent variables, outperforming existing methods on synthetic and real data.

Contribution

We propose a novel variational neural framework for temporal point processes that effectively captures diverse event types and improves prediction accuracy.

Findings

Outperforms existing neural and statistical models on multiple datasets.

Effectively models and predicts various event types.

Demonstrates improved generalization and accuracy in event timing and type prediction.

Abstract

A temporal point process is a stochastic process that predicts which type of events is likely to happen and when the event will occur given a history of a sequence of events. There are various examples of occurrence dynamics in the daily life, and it is important to train the temporal dynamics and solve two different prediction problems, time and type predictions. Especially, deep neural network based models have outperformed the statistical models, such as Hawkes processes and Poisson processes. However, many existing approaches overfit to specific events, instead of learning and predicting various event types. Therefore, such approaches could not cope with the modified relationships between events and fail to predict the intensity functions of temporal point processes very well. In this paper, to solve these problems, we propose a variational neural temporal point process (VNTPP). We introduce the inference and the generative networks, and train a distribution of latent variable to deal with stochastic property on deep neural network. The intensity functions are computed using the distribution of latent variable so that we can predict event types and the arrival times of the events more accurately. We empirically demonstrate that our model can generalize the representations of various event types. Moreover, we show quantitatively and qualitatively that our model outperforms other deep neural network based models and statistical processes on synthetic and real-world datasets.