Neural multi-event forecasting on spatio-temporal point processes using probabilistically enriched transformers

Negar Erfanian, Santiago Segarra, Maarten V. de Hoop

Keywords: Stochastic Point Processes, Multi-event Prediction, Transformers, Normalizing Flows, Hawkes Process, Deep Learning, Generative Models

TL;DR: In this work, we introduce a novel neural network that is capable of simultaneous multi-event forecasting of spatio-temporal distributions associated with stochastic discrete events.

Abstract: Predicting discrete events in time and space has many scientific applications, such as predicting hazardous earthquakes and outbreaks of infectious diseases. History-dependent spatio-temporal Hawkes processes are often used to mathematically model these point events. However, previous approaches have faced numerous challenges, particularly when attempting to forecast multiple future events. In this work, we propose a new neural architecture for multi-event forecasting of spatio-temporal point processes, utilizing transformers, augmented with normalizing flows and probabilistic layers. Our network makes batched predictions of complex history-dependent spatio-temporal distributions of future discrete events, achieving state-of-the-art performance on a variety of benchmark datasets including the South California Earthquakes, Citibike, Covid19, and Hawkes synthetic Pinwheel datasets. More generally, we illustrate how our network can be applied to any dataset of discrete events with associated markers, even when no underlying physics is known.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

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

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2211.02922/code)