Variational Neural Temporal Point Process

02/17/2022
by   Deokjun Eom, et al.
0

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.

READ FULL TEXT

page 3

page 6

research
12/12/2021

Neural Point Process for Learning Spatiotemporal Event Dynamics

Learning the dynamics of spatiotemporal events is a fundamental problem....
research
01/14/2017

Marked Temporal Dynamics Modeling based on Recurrent Neural Network

We are now witnessing the increasing availability of event stream data, ...
research
06/20/2023

Deep graph kernel point processes

Point process models are widely used to analyze asynchronous events occu...
research
07/28/2020

Universal Approximation with Neural Intensity Point Processes

We propose a class of neural network models that universally approximate...
research
02/12/2013

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

We propose a latent self-exciting point process model that describes geo...
research
05/05/2020

Event Cartography: Latent Point Process Embeddings

Many important phenomena arise naturally as temporal point processes wit...
research
10/19/2021

An Empirical Study: Extensive Deep Temporal Point Process

Temporal point process as the stochastic process on continuous domain of...

Please sign up or login with your details

Forgot password? Click here to reset