A Multi-Channel Neural Graphical Event Model with Negative Evidence

02/21/2020
by   Tian Gao, et al.
0

Event datasets are sequences of events of various types occurring irregularly over the time-line, and they are increasingly prevalent in numerous domains. Existing work for modeling events using conditional intensities rely on either using some underlying parametric form to capture historical dependencies, or on non-parametric models that focus primarily on tasks such as prediction. We propose a non-parametric deep neural network approach in order to estimate the underlying intensity functions. We use a novel multi-channel RNN that optimally reinforces the negative evidence of no observable events with the introduction of fake event epochs within each consecutive inter-event interval. We evaluate our method against state-of-the-art baselines on model fitting tasks as gauged by log-likelihood. Through experiments on both synthetic and real-world datasets, we find that our proposed approach outperforms existing baselines on most of the datasets studied.

READ FULL TEXT
research
10/18/2019

Point Process Flows

Event sequences can be modeled by temporal point processes (TPPs) to cap...
research
06/03/2020

Shallow Neural Hawkes: Non-parametric kernel estimation for Hawkes processes

Multi-dimensional Hawkes process (MHP) is a class of self and mutually e...
research
04/16/2021

Interval-censored Hawkes processes

This work builds a novel point process and tools to use the Hawkes proce...
research
02/13/2023

Continuous-time convolutions model of event sequences

Massive samples of event sequences data occur in various domains, includ...
research
03/09/2019

Variational Inference of Joint Models using Multivariate Gaussian Convolution Processes

We present a non-parametric prognostic framework for individualized even...

Please sign up or login with your details

Forgot password? Click here to reset