Skip to main navigation Skip to search Skip to main content

Continuous-Time Stochastic Differential Networks for Irregular Time Series Modeling

  • Yingru Liu
  • , Yucheng Xing
  • , Xuewen Yang
  • , Xin Wang
  • , Jing Shi
  • , Di Jin
  • , Zhaoyue Chen
  • , Jacqueline Wu
  • Stony Brook University
  • University of Rochester
  • Amazon.com, Inc.
  • Ward Melville High School

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling irregular time series, whose observations are irregular and sparse in both time and dimension. For a given system whose latent states and observed data are multivariate, it is generally impossible to derive a precise continuous-time stochastic process to describe the system behaviors. To solve the above problem, we apply Variational Bayesian method and propose a flexible continuous-time stochastic recurrent neural network named Variational Stochastic Differential Networks (VSDN), which embeds the complicated dynamics of the irregular time series by neural Stochastic Differential Equations (SDE). VSDNs capture the stochastic dependency among latent states and observations by deep neural networks. We also incorporate two differential Evidence Lower Bounds to efficiently train the models. Through comprehensive experiments, we show that VSDNs outperform state-of-the-art continuous-time deep learning models and achieve remarkable performance on prediction and interpolation tasks for irregular time series.

Original languageEnglish
Title of host publicationNeural Information Processing - 28th International Conference, ICONIP 2021, Proceedings
EditorsTeddy Mantoro, Minho Lee, Media Anugerah Ayu, Kok Wai Wong, Achmad Nizar Hidayanto
PublisherSpringer Science and Business Media Deutschland GmbH
Pages343-351
Number of pages9
ISBN (Print)9783030923068
DOIs
StatePublished - 2021
Event28th International Conference on Neural Information Processing, ICONIP 2021 - Virtual, Online
Duration: Dec 8 2021Dec 12 2021

Publication series

NameCommunications in Computer and Information Science
Volume1516 CCIS

Conference

Conference28th International Conference on Neural Information Processing, ICONIP 2021
CityVirtual, Online
Period12/8/2112/12/21

Keywords

  • Irregular time series
  • Neural Stochastic Differential Equations
  • Stochastic recurrent neural network

Fingerprint

Dive into the research topics of 'Continuous-Time Stochastic Differential Networks for Irregular Time Series Modeling'. Together they form a unique fingerprint.

Cite this