OptiGAN: generative Adversarial Networks for goal optimized sequence generation

Trung Le, Viet Huynh, Michael Papasimeon, Dinh Phung

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

Abstract

One of the challenging problems in sequence generation tasks is the optimized generation of sequences with specific desired goals. Current sequential generative models mainly generate sequences to closely mimic the training data, without direct optimization of desired goals or properties specific to the task. We introduce OptiGAN, a generative model that incorporates both Generative Adversarial Networks (GAN) and Reinforcement Learning (RL) to optimize desired goal scores using policy gradients. We apply our model to text and real-valued sequence generation, where our model is able to achieve higher desired scores out-performing GAN and RL baselines, while not sacrificing output sample diversity.

Original languageEnglish
Title of host publication2020 International Joint Conference on Neural Networks (IJCNN), 2020 Conference Proceedings2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
EditorsAsim Roy
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages8
ISBN (Electronic)9781728169262
ISBN (Print)9781728169279
DOIs
Publication statusPublished - 2020
EventIEEE International Joint Conference on Neural Networks 2020 - Virtual, Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020
https://ieeexplore.ieee.org/xpl/conhome/9200848/proceeding (Proceedings)
https://wcci2020.org/ijcnn-sessions/ (Website)

Publication series

NameProceedings of the International Joint Conference on Neural Networks
PublisherIEEE
ISSN (Print)2161-4393
ISSN (Electronic)2161-4407

Conference

ConferenceIEEE International Joint Conference on Neural Networks 2020
Abbreviated titleIJCNN 2020
CountryUnited Kingdom
CityVirtual, Glasgow
Period19/07/2024/07/20
Internet address

Keywords

  • Generative Adversarial Networks
  • Policy Gradients
  • Reinforcement Learning
  • Sequential Data

Cite this