EventFlow: Forecasting Temporal Point Processes with Flow Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kerrigan, Gavin, Nelson, Kai, Smyth, Padhraic
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911567992324096
author Kerrigan, Gavin
Nelson, Kai
Smyth, Padhraic
author_facet Kerrigan, Gavin
Nelson, Kai
Smyth, Padhraic
contents Continuous-time event sequences, in which events occur at irregular intervals, are ubiquitous across a wide range of industrial and scientific domains. The contemporary modeling paradigm is to treat such data as realizations of a temporal point process, and in machine learning it is common to model temporal point processes in an autoregressive fashion using a neural network. While autoregressive models are successful in predicting the time of a single subsequent event, their performance can degrade when forecasting longer horizons due to cascading errors and myopic predictions. We propose EventFlow, a non-autoregressive generative model for temporal point processes. The model builds on the flow matching framework in order to directly learn joint distributions over event times, side-stepping the autoregressive process. EventFlow is simple to implement and achieves a 20%-53% lower forecast error than the nearest baseline on standard TPP benchmarks while simultaneously using fewer model calls at sampling time.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07430
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EventFlow: Forecasting Temporal Point Processes with Flow Matching
Kerrigan, Gavin
Nelson, Kai
Smyth, Padhraic
Machine Learning
Continuous-time event sequences, in which events occur at irregular intervals, are ubiquitous across a wide range of industrial and scientific domains. The contemporary modeling paradigm is to treat such data as realizations of a temporal point process, and in machine learning it is common to model temporal point processes in an autoregressive fashion using a neural network. While autoregressive models are successful in predicting the time of a single subsequent event, their performance can degrade when forecasting longer horizons due to cascading errors and myopic predictions. We propose EventFlow, a non-autoregressive generative model for temporal point processes. The model builds on the flow matching framework in order to directly learn joint distributions over event times, side-stepping the autoregressive process. EventFlow is simple to implement and achieves a 20%-53% lower forecast error than the nearest baseline on standard TPP benchmarks while simultaneously using fewer model calls at sampling time.
title EventFlow: Forecasting Temporal Point Processes with Flow Matching
topic Machine Learning
url https://arxiv.org/abs/2410.07430