Back to Search Start Over

Meta Temporal Point Processes

Meta Temporal Point Processes

Authors :
Bae, Wonho
Ahmed, Mohamed Osama
Tung, Frederick
Oliveira, Gabriel L.
Publication Year :
2023

Abstract

A temporal point process (TPP) is a stochastic process where its realization is a sequence of discrete events in time. Recent work in TPPs model the process using a neural network in a supervised learning framework, where a training set is a collection of all the sequences. In this work, we propose to train TPPs in a meta learning framework, where each sequence is treated as a different task, via a novel framing of TPPs as neural processes (NPs). We introduce context sets to model TPPs as an instantiation of NPs. Motivated by attentive NP, we also introduce local history matching to help learn more informative features. We demonstrate the potential of the proposed method on popular public benchmark datasets and tasks, and compare with state-of-the-art TPP methods.<br />Comment: Accepted to ICLR2023

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2301.12023
Document Type :
Working Paper