Supervised and Unsupervised Coupled Generative Adversarial Networks in Multivariate Time Series

Qinfen Wang, Yifei Li, Yong Xia

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

Abstract

Generative adversarial networks (GAN) have been successful in demonstrating the efficiency of generative time series. In this paper, we proposed a novel end-to-end supervised and unsupervised coupled generative adversarial networks (SUC-GAN) framework that consists of a gated recurrent unit (GRU) for generating multivariate time series. We test SUC-GAN on three datasets (i.e. Sines, Energy, Stocks) to investigate the efficacy and properties. The preliminary results show the potential power of supervised, unsupervised, and coupled learning for data generation.

Original languageEnglish
Title of host publication2023 4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages198-201
Number of pages4
ISBN (Electronic)9798350337181
DOIs
StatePublished - 2023
Event4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023 - Hybrid, Guangzhou, China
Duration: 14 Jul 202316 Jul 2023

Publication series

Name2023 4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023

Conference

Conference4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023
Country/TerritoryChina
CityHybrid, Guangzhou
Period14/07/2316/07/23

Keywords

  • coupled learning
  • GAN
  • multivariate time series

Fingerprint

Dive into the research topics of 'Supervised and Unsupervised Coupled Generative Adversarial Networks in Multivariate Time Series'. Together they form a unique fingerprint.

Cite this