research-article

Multi-objective evolutionary GAN

Authors:

Marco Baioletti,

Carlos Artemio Coello Coello,

Gabriele Di Bari,

Valentina PoggioniAuthors Info & Claims

GECCO '20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion

Pages 1824 - 1831

https://doi.org/10.1145/3377929.3398138

Published: 08 July 2020 Publication History

Abstract

Generative Adversarial Network (GAN) is a generative model proposed to imitate real data distributions. The original GAN algorithm has been found to be able to achieve excellent results for the image generation task, but it suffers from problems such as instability and mode collapse. To tackle these problems, many variants of the original model have been proposed; one of them is the Evolutionary GAN (EGAN), where a population of generators is evolved.

Inspired by EGAN, we propose here a new algorithm, called Multi-Objective Evolutionary Generative Adversarial Network (MOEGAN), which reformulates the problem of training GANs as a multi-objective optimization problem. Thus, Pareto dominance is used to select the best solutions, evaluated using diversity and quality fitness functions.

Preliminary experimental results on synthetic datasets show how the proposed approach can achieve better results than EGAN.

References

[1]

Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and TAMT Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. <u>IEEE transactions on evolutionary computation</u> 6, 2 (2002), 182--197.

[2]

J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In <u>CVPR09.</u>

[3]

Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In <u>Advances in neural information processing systems.</u> 2672--2680.

[4]

Arthur Gretton, Karsten M Borgwardt, Malte J Rasch, Bernhard Schölkopf, and Alexander Smola. 2012. A kernel two-sample test. <u>Journal of Machine Learning Research</u> 13, Mar (2012), 723--773.

[5]

Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron Courville. 2017. Improved Training of Wasserstein GANs. In <u>Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17).</u> Curran Associates Inc., Red Hook, NY, USA, 5769--5779.

[6]

Alex Krizhevsky. 2009. <u>Learning multiple layers of features from tiny images.</u> Technical Report.

[7]

Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. 2015. Deep Learning Face Attributes in the Wild. In <u>Proceedings of International Conference on Computer Vision (ICCV).</u>

[8]

Xudong Mao, Qing Li, Haoran Xie, Raymond YK Lau, Zhen Wang, and Stephen Paul Smolley. 2017. Least squares generative adversarial networks. In <u>Proceedings of the IEEE International Conference on Computer Vision.</u> 2794--2802.

[9]

Z. Pan, W. Yu, X. Yi, A. Khan, F. Yuan, and Y. Zheng. 2019. Recent Progress on Generative Adversarial Networks (GANs): A Survey. <u>IEEE Access</u> 7 (2019), 36322--36333.

[10]

Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic Backpropagation and Approximate Inference in Deep Generative Models. In <u>Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32 (ICML'14).</u> JMLR.org, II-1278--II-1286.

[11]

Alex Smola, Arthur Gretton, Le Song, and Bernhard Schölkopf. 2007. A Hilbert space embedding for distributions. In <u>International Conference on Algorithmic Learning Theory.</u> Springer, 13--31.

[12]

Jamal Toutouh, Erik Hemberg, and Una-May O'Reilly. 2019. Spatial evolutionary generative adversarial networks. In <u>Proceedings of the Genetic and Evolutionary Computation Conference.</u> 472--480.

[13]

Aäron van den Oord and Nal Kalchbrenner. 2016. Pixel RNN. In <u>ICML.</u>

[14]

Aäron van den Oord, Nal Kalchbrenner, Lasse Espeholt, Koray Kavukcuoglu, Oriol Vinyals, and Alexander Graves. 2016. Conditional Image Generation with PixelCNN Decoders. In <u>Advances in Neural Information Processing Systems 29.</u> 4790--4798.

[15]

Chaoyue Wang, Chang Xu, Xin Yao, and Dacheng Tao. 2019. Evolutionary generative adversarial networks. <u>IEEE Transactions on Evolutionary Computation</u> 23, 6 (2019), 921--934.

[16]

Zhengwei Wang, Qi She, and Tomas E Ward. 2019. Generative adversarial networks: A survey and taxonomy. <u>arXiv preprint arXiv:1906.01529</u> (2019).

[17]

Xian Wu, Kun Xu, and Peter Hall. 2017. A survey of image synthesis and editing with generative adversarial networks. <u>Tsinghua Science and Technology</u> 22, 6 (2017), 660--674.

[18]

Han Xiao, Kashif Rasul, and Roland Vollgraf. 2017. <u>Fashion-MNIST</u>: <u>a Novel Image Dataset for Benchmarking Machine Learning Algorithms.</u> arXiv:cs.LG/cs.LG/1708.07747

[19]

Fisher Yu, Yinda Zhang, Shuran Song, Ari Seff, and Jianxiong Xiao. 2015. LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. <u>arXiv preprint arXiv:1506.03365</u> (2015).

Cited By

Toutouh JO'Reilly ULi XHandl J(2024)Coevolutionary Computation for Adversarial Deep LearningProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3638530.3648405(1410-1431)Online publication date: 14-Jul-2024
https://dl.acm.org/doi/10.1145/3638530.3648405
Li MPei XLiang XYu QJia WJian LShi Z(2024)GEGAN: Generative Adversarial Networks Training Based on Gradient Directed Evolutionary Strategy2024 9th International Conference on Signal and Image Processing (ICSIP)10.1109/ICSIP61881.2024.10671562(481-486)Online publication date: 12-Jul-2024
https://doi.org/10.1109/ICSIP61881.2024.10671562
Shang QYang JMa J(2024)Multi-branch evolutionary generative adversarial networks based on covariance crossover operatorsKnowledge-Based Systems10.1016/j.knosys.2024.112527304(112527)Online publication date: Nov-2024
https://doi.org/10.1016/j.knosys.2024.112527
Show More Cited By

Index Terms

Multi-objective evolutionary GAN
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
    1. Machine learning approaches
      1. Bio-inspired approaches
      2. Neural networks

Index terms have been assigned to the content through auto-classification.

Recommendations

Genetic diversity as an objective in multi-objective evolutionary algorithms

A key feature of an efficient and reliable multi-objective evolutionary algorithm is the ability to maintain genetic diversity within a population of solutions. In this paper, we present a new diversity-preserving mechanism, the Genetic Diversity ...
An analysis on recombination in multi-objective evolutionary optimization

Evolutionary algorithms (EAs) are increasingly popular approaches to multi-objective optimization. One of their significant advantages is that they can directly optimize the Pareto front by evolving a population of solutions, where the recombination (...
A mutation operator based on a Pareto ranking for multi-objective evolutionary algorithms

Evolutionary Algorithms, EA's, try to imitate, in some way, the principles of natural evolution and genetics. They evolve a population of potential solutions to the problem using operators such as mutation, crossover and selection. In general, the ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

GECCO '20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion

July 2020

1982 pages

ISBN:9781450371278

DOI:10.1145/3377929

General Chair:
Carlos Artemio Coello Coello
CINVESTAV-IPN

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGEVO: ACM Special Interest Group on Genetic and Evolutionary Computation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 July 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

GECCO '20

Sponsor:

SIGEVO

GECCO '20: Genetic and Evolutionary Computation Conference

July 8 - 12, 2020

Cancún, Mexico

Acceptance Rates

Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
397
Total Downloads

Downloads (Last 12 months)57
Downloads (Last 6 weeks)9

Reflects downloads up to 23 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Toutouh JO'Reilly ULi XHandl J(2024)Coevolutionary Computation for Adversarial Deep LearningProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3638530.3648405(1410-1431)Online publication date: 14-Jul-2024
https://dl.acm.org/doi/10.1145/3638530.3648405
Li MPei XLiang XYu QJia WJian LShi Z(2024)GEGAN: Generative Adversarial Networks Training Based on Gradient Directed Evolutionary Strategy2024 9th International Conference on Signal and Image Processing (ICSIP)10.1109/ICSIP61881.2024.10671562(481-486)Online publication date: 12-Jul-2024
https://doi.org/10.1109/ICSIP61881.2024.10671562
Shang QYang JMa J(2024)Multi-branch evolutionary generative adversarial networks based on covariance crossover operatorsKnowledge-Based Systems10.1016/j.knosys.2024.112527304(112527)Online publication date: Nov-2024
https://doi.org/10.1016/j.knosys.2024.112527
Wang YZhang QWang GCheng H(2024)The application of evolutionary computation in generative adversarial networks (GANs): a systematic literature surveyArtificial Intelligence Review10.1007/s10462-024-10818-y57:7Online publication date: 21-Jun-2024
https://doi.org/10.1007/s10462-024-10818-y
Cao BLei H(2023)LGEGAN: A Lightweight Evolutionary Generative Adversarial Network with Statistic Global Information2023 42nd Chinese Control Conference (CCC)10.23919/CCC58697.2023.10241151(8282-8287)Online publication date: 24-Jul-2023
https://doi.org/10.23919/CCC58697.2023.10241151
Tao QXiong ZHan BFan XLi L(2023)A Novel Unsupervised Approach for Cross-Lingual Word Alignment in Low Isomorphic Embedding SpacesIEEE/ACM Transactions on Audio, Speech, and Language Processing10.1109/TASLP.2023.330120831(3027-3041)Online publication date: 2023
https://doi.org/10.1109/TASLP.2023.3301208
Toutouh JHemberg EO’Reilly U(2023)Adversarial Evolutionary Learning with Distributed Spatial CoevolutionHandbook of Evolutionary Machine Learning10.1007/978-981-99-3814-8_13(397-435)Online publication date: 2-Nov-2023
https://doi.org/10.1007/978-981-99-3814-8_13
Wang GThite ATalebi RD'Achille AMussa AZutty JWagner M(2022)Evolving SimGANs to improve abnormal electrocardiogram classificationProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3520304.3534048(1887-1894)Online publication date: 9-Jul-2022
https://dl.acm.org/doi/10.1145/3520304.3534048
Liu FWang HZhang JFu ZZhou AQi JLi Z(2022)EvoGAN: An evolutionary computation assisted GANNeurocomputing10.1016/j.neucom.2021.10.060469(81-90)Online publication date: Jan-2022
https://doi.org/10.1016/j.neucom.2021.10.060
Bharti VBiswas BShukla K(2022)Swarm Intelligence for Deep Learning: Concepts, Challenges and Recent TrendsAdvances in Swarm Intelligence10.1007/978-3-031-09835-2_3(37-57)Online publication date: 2-Oct-2022
https://doi.org/10.1007/978-3-031-09835-2_3
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten