Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

Using Skill Rating as Fitness on the Evolution of GANs

  • Conference paper
  • First Online:

Part of the book series:Lecture Notes in Computer Science ((LNTCS,volume 12104))

  • 1343Accesses

Abstract

Generative Adversarial Networks (GANs) are an adversarial model that achieved impressive results on generative tasks. In spite of the relevant results, GANs present some challenges regarding stability, making the training usually a hit-and-miss process. To overcome these challenges, several improvements were proposed to better handle the internal characteristics of the model, such as alternative loss functions or architectural changes on the neural networks used by the generator and the discriminator. Recent works proposed the use of evolutionary algorithms on GAN training, aiming to solve these challenges and to provide an automatic way to find good models. In this context, COEGAN proposes the use of coevolution and neuroevolution to orchestrate the training of GANs. However, previous experiments detected that some of the fitness functions used to guide the evolution are not ideal.

In this work we propose the evaluation of a game-based fitness function to be used within the COEGAN method. Skill rating is a metric to quantify the skill of players in a game and has already been used to evaluate GANs. We extend this idea using the skill rating in an evolutionary algorithm to train GANs. The results show that skill rating can be used as fitness to guide the evolution in COEGAN without the dependence of an external evaluator.

This is a preview of subscription content,log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 5719
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 7149
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Similar content being viewed by others

References

  1. Al-Dujaili, A., Schmiedlechner, T., Hemberg, E., O’Reilly, U.M.: Towards distributed coevolutionary GANs. In: AAAI 2018 Fall Symposium (2018)

    Google Scholar 

  2. Antonio, L.M., Coello, C.A.C.: Coevolutionary multiobjective evolutionary algorithms: survey of the state-of-the-art. IEEE Trans. Evol. Comput.22(6), 851–865 (2018)

    Article  Google Scholar 

  3. Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)

    Google Scholar 

  4. Borji, A.: Pros and cons of GAN evaluation measures. Comput. Vis. Image Underst.179, 41–65 (2019)

    Article  Google Scholar 

  5. Costa, V., Lourenço, N., Correia, J., Machado, P.: COEGAN: evaluating the coevolution effect in generative adversarial networks. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 374–382. ACM (2019)

    Google Scholar 

  6. Costa, V., Lourenço, N., Machado, P.: Coevolution of generative adversarial networks. In: Kaufmann, P., Castillo, P.A. (eds.) EvoApplications 2019. LNCS, vol. 11454, pp. 473–487. Springer, Cham (2019).https://doi.org/10.1007/978-3-030-16692-2_32

    Chapter  Google Scholar 

  7. Garciarena, U., Santana, R., Mendiburu, A.: Evolved GANs for generating pareto set approximations. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2018, pp. 434–441. ACM, New York (2018)

    Google Scholar 

  8. Glickman, M.E.: Example of the Glicko-2 system, pp. 1–6. Boston University (2013).http://www.glicko.net/glicko/glicko2.pdf

  9. Goodfellow, I., et al.: Generative adversarial nets. In: NIPS. Curran Associates, Inc. (2014)

    Google Scholar 

  10. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5769–5779 (2017)

    Google Scholar 

  11. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6629–6640 (2017)

    Google Scholar 

  12. Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. In: International Conference on Learning Representations (2019)

    Google Scholar 

  13. Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (2018)

    Google Scholar 

  14. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)

    Google Scholar 

  15. LeCun, Y.: The MNIST database of handwritten digits (1998).http://yann.lecun.com/exdb/mnist/

  16. Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2813–2821. IEEE (2017)

    Google Scholar 

  17. Miikkulainen, R., et al.: Evolving deep neural networks. arXiv preprintarXiv:1703.00548 (2017)

  18. Mitchell, M.: Coevolutionary learning with spatially distributed populations. In: Computational Intelligence: Principles and Practice (2006)

    Google Scholar 

  19. Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)

    Google Scholar 

  20. Olsson, C., Bhupatiraju, S., Brown, T., Odena, A., Goodfellow, I.: Skill rating for generative models. arXiv preprintarXiv:1808.04888 (2018)

  21. Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprintarXiv:1511.06434 (2015)

  22. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis.115(3), 211–252 (2015).https://doi.org/10.1007/s11263-015-0816-y

    Article MathSciNet  Google Scholar 

  23. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, pp. 2234–2242 (2016)

    Google Scholar 

  24. Sims, K.: Evolving 3D morphology and behavior by competition. Artif. Life1(4), 353–372 (1994)

    Article  Google Scholar 

  25. Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput.10(2), 99–127 (2002)

    Article  Google Scholar 

  26. Stanley, K.O., Miikkulainen, R.: Competitive coevolution through evolutionary complexification. J. Artif. Intell. Res.21, 63–100 (2004)

    Article  Google Scholar 

  27. Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)

    Google Scholar 

  28. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)

    Google Scholar 

  29. Toutouh, J., Hemberg, E., O’Reilly, U.M.: Spatial evolutionary generative adversarial networks. arXiv preprintarXiv:1905.12702 (2019)

  30. Veček, N., Črepinšek, M., Mernik, M., Hrnčič, D.: A comparison between different chess rating systems for ranking evolutionary algorithms. In: 2014 Federated Conference on Computer Science and Information Systems, pp. 511–518. IEEE (2014)

    Google Scholar 

  31. Veček, N., Mernik, M., Črepinšek, M.: A chess rating system for evolutionary algorithms: a new method for the comparison and ranking of evolutionary algorithms. Inf. Sci.277, 656–679 (2014)

    Article MathSciNet  Google Scholar 

  32. Wang, C., Xu, C., Yao, X., Tao, D.: Evolutionary generative adversarial networks. arXiv preprintarXiv:1803.00657 (2018)

  33. Xu, Q., et al.: An empirical study on evaluation metrics of generative adversarial networks. arXiv preprintarXiv:1806.07755 (2018)

  34. Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprintarXiv:1805.08318 (2018)

Download references

Acknowledgments

This article is based upon work from COST Action CA15140: ImAppNIO, supported by COST (European Cooperation in Science and Technology).

Author information

Authors and Affiliations

  1. CISUC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal

    Victor Costa, Nuno Lourenço, João Correia & Penousal Machado

Authors
  1. Victor Costa

    You can also search for this author inPubMed Google Scholar

  2. Nuno Lourenço

    You can also search for this author inPubMed Google Scholar

  3. João Correia

    You can also search for this author inPubMed Google Scholar

  4. Penousal Machado

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence toVictor Costa,Nuno Lourenço,João Correia orPenousal Machado.

Editor information

Editors and Affiliations

  1. University of Granada, Granada, Spain

    Pedro A. Castillo

  2. Université Le Havre Normandie, Le Havre, France

    Juan Luis Jiménez Laredo

  3. Universidad de Extremadura, Mérida, Spain

    Francisco Fernández de Vega

Rights and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Costa, V., Lourenço, N., Correia, J., Machado, P. (2020). Using Skill Rating as Fitness on the Evolution of GANs. In: Castillo, P.A., Jiménez Laredo, J.L., Fernández de Vega, F. (eds) Applications of Evolutionary Computation. EvoApplications 2020. Lecture Notes in Computer Science(), vol 12104. Springer, Cham. https://doi.org/10.1007/978-3-030-43722-0_36

Download citation

Publish with us

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 5719
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 7149
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

[8]ページ先頭
©2009-2025 Movatter.jp