Memory-Gated Recurrent Networks

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

  • Yaquan Zhang
  • Nanbo Peng
  • Min Dai
  • Hu Wang

Detail(s)

Original languageEnglish
Title of host publicationThe Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)
PublisherAAAI Press
Pages10956-10963
ISBN (Print)978-1-57735-866-4 (set)
Publication statusPublished - Feb 2021

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAAAI Press
Number12
Volume35
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Title35th AAAI Conference on Artificial Intelligence (AAAI-21)
LocationVirtual
Period2 - 9 February 2021

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.

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

Memory-Gated Recurrent Networks. / Zhang, Yaquan; Wu, Qi; Peng, Nanbo; Dai, Min; Zhang, Jing; Wang, Hu.

The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21). AAAI Press, 2021. p. 10956-10963 (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 35, No. 12).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review