Memory-Gated Recurrent Networks

Yaquan Zhang, Qi Wu, Nanbo Peng, Min Dai, Jing Zhang, Hu Wang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

The essence of multivariate sequential learning is all about how to extract dependencies in data. These data sets, such as hourly medical records in intensive care units and multi-frequency phonetic time series, often time exhibit not only strong serial dependencies in the individual components (the “marginal” memory) but also non-negligible memories in the cross-sectional dependencies (the “joint” memory). Because of the multivariate complexity in the evolution of the joint distribution that underlies the data generating process, we take a data-driven approach and construct a novel recurrent network architecture, termed Memory-Gated Recurrent Networks (mGRN), with gates explicitly regulating two distinct types of memories: the marginal memory and the joint memory. Through a combination of comprehensive simulation studies and empirical experiments on a range of public datasets, we show that our proposed mGRN architecture consistently outperforms state-of-the-art architectures targeting multivariate time series.

Original languageEnglish
Title of host publication35th AAAI Conference on Artificial Intelligence, AAAI 2021
PublisherAssociation for the Advancement of Artificial Intelligence
Pages10956-10963
Number of pages8
Volume12B
ISBN (Electronic)9781713835974
Publication statusPublished - Feb 2021
Event35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online
Duration: 2 Feb 20219 Feb 2021

Publication series

Name35th AAAI Conference on Artificial Intelligence, AAAI 2021
Volume12B

Conference

Conference35th AAAI Conference on Artificial Intelligence, AAAI 2021
CityVirtual, Online
Period2/02/219/02/21

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this