Neural Spatio-Temporal Point ProcessesDownload PDF

Published: 12 Jan 2021, Last Modified: 22 Oct 2023ICLR 2021 PosterReaders: Everyone
Keywords: point processes, normalizing flows, differential equations
Abstract: We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are localized in continuous time and space. Central to our approach is a combination of continuous-time neural networks with two novel neural architectures, \ie, Jump and Attentive Continuous-time Normalizing Flows. This approach allows us to learn complex distributions for both the spatial and temporal domain and to condition non-trivially on the observed event history. We validate our models on data sets from a wide variety of contexts such as seismology, epidemiology, urban mobility, and neuroscience.
One-sentence Summary: We motivate the use of Continuous-time Normalizing Flows for building spatio-temporal point processes, and discuss modeling conditional dependencies with recurrent- or attention-based Neural ODEs.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [![github](/images/github_icon.svg) facebookresearch/neural_stpp](
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
12 Replies