The Library
MGGAN : Improving sample generations of Generative Adversarial Networks
Tools
Tools
Tools
Wu, Hao, He, Ligang, Li, Chang-Tsun, Li, Junyu, Wu, Wentai and Maple, Carsten (2022) MGGAN : Improving sample generations of Generative Adversarial Networks. In: 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys), Haikou, Hainan, China, 20-22 Dec 2021. Published in: 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys) ISBN 9781665494571. doi:10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00073
|
PDF
WRAP-MGGAN-improving-sample-generations-generative-adversarial-networks-2022.pdf - Submitted Version - Requires a PDF viewer. Download (5Mb) | Preview |
Official URL: https://doi.org/10.1109/HPCC-DSS-SmartCity-DependS...
Abstract
Generative adversarial networks (GANs) are powerful generative models that are widely used to produce synthetic data. This paper proposes a Multi-Group Generative Adversarial Network (MGGAN), a framework that consists of multiple generative groups for addressing the mode collapse problem and creating high-quality samples with less time cost. The idea is intuitive yet effective. The distinguishing characteristic of MGGAN is that a generative group includes a fixed generator but a dynamic discriminator. All the generators need to combine with a random discriminator from other generative groups after a certain number of training iterations, which is called regrouping. The multiple generative groups are trained simultaneously and independently without sharing the parameters. The learning rate and the regrouping interval are adjusted dynamically in the training process. We conduct extensive experiments on the synthetic and real-world datasets. The experimental results show the superior performance of our MGGAN in generating high quality and diverse samples with less training time.
| Item Type: | Conference Item (Paper) | ||||
|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||
| SWORD Depositor: | Library Publications Router | ||||
| Library of Congress Subject Headings (LCSH): | Generative programming (Computer science), Neural networks (Computer science), Machine learning, Artificial intelligence | ||||
| Journal or Publication Title: | 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys) | ||||
| Publisher: | IEEE | ||||
| ISBN: | 9781665494571 | ||||
| Official Date: | 29 May 2022 | ||||
| Dates: |
|
||||
| DOI: | 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00073 | ||||
| Status: | Peer Reviewed | ||||
| Publication Status: | Published | ||||
| Access rights to Published version: | Restricted or Subscription Access | ||||
| Conference Paper Type: | Paper | ||||
| Title of Event: | 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys) | ||||
| Type of Event: | Conference | ||||
| Location of Event: | Haikou, Hainan, China | ||||
| Date(s) of Event: | 20-22 Dec 2021 |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
