An Empirical Study: Extensive Deep Temporal Point Process

Abstract

Temporal point process as the stochastic process on continuous domain of time is commonly used to model the asynchronous event sequence featuring with occurrence timestamps. Thanks to the strong expressivity of deep neural networks, they are emerging as a promising choice for capturing the patterns in asynchronous sequences, in the context of temporal point process. In this paper, we first review recent research emphasis and difficulties in modeling asynchronous event sequences with deep temporal point process, which can be concluded into four fields: encoding of history sequence, formulation of conditional intensity function, relational discovery of events and learning approaches for optimization. We introduce most of recently proposed models by dismantling them into the four parts, and conduct experiments by remodularizing the first three parts with the same learning strategy for a fair empirical evaluation. Besides, we extend the history encoders and conditional intensity function family, and propose a Granger causality discovery framework for exploiting the relations among multi-types of events. Because the Granger causality can be represented by the Granger causality graph, discrete graph structure learning in the framework of Variational Inference is employed to reveal latent structures of the graph. Further experiments show that the proposed framework with latent graph discovery can both capture the relations and achieve an improved fitting and predicting performance.

22 pages, 8 figures

References in corpus (20)

• Auto-Encoding Variational Bayes
• Categorical Reparameterization with Gumbel-Softmax
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Neural Ordinary Differential Equations
• BRITS: Bidirectional Recurrent Imputation for Time Series
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Latent ODEs for Irregularly-Sampled Time Series
• Neural Jump Stochastic Differential Equations
• Fully Neural Network based Model for General Temporal Point Processes
• Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth
• Deep Reinforcement Learning of Marked Temporal Point Processes
• Learning Temporal Point Processes via Reinforcement Learning
• Rethinking Positional Encoding
• Transformer Hawkes Process
• Quantifying the vanishing gradient and long distance dependency problem in recursive neural networks and recursive LSTMs
• Contrastive Graph Neural Network Explanation
• CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods
• Graphical Modeling for Multivariate Hawkes Processes with Nonparametric Link Functions
• Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View
• Statistical Inference for Mixture of Cauchy Distributions