Skip to main content
SpringerLink
Log in

Games of GANs: game-theoretical models for generative adversarial networks

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

Generative Adversarial Networks (GANs) have recently attracted considerable attention in the AI community due to their ability to generate high-quality data of significant statistical resemblance to real data. Fundamentally, GAN is a game between two neural networks trained in an adversarial manner to reach a zero-sum Nash equilibrium profile. Despite the improvement accomplished in GANs in the last few years, several issues remain to be solved. This paper reviews the literature on the game-theoretic aspects of GANs and addresses how game theory models can address specific challenges of generative models and improve the GAN’s performance. We first present some preliminaries, including the basic GAN model and some game theory background. We then present a taxonomy to classify state-of-the-art solutions into three main categories: modified game models, modified architectures, and modified learning methods. The classification is based on modifications made to the basic GAN model by proposed game-theoretic approaches in the literature. We then explore the objectives of each category and discuss recent works in each class. Finally, we discuss the remaining challenges in this field and present future research directions.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  • Aghakhani H, Machiry A, Nilizadeh S, Kruegel C, Vigna G (2018) Detecting deceptive reviews using generative adversarial networks. In: Proceedings IEEE security and privacy workshops (SPW), San Francisco, pp 89–95

  • Agnese J, Herrera J, Tao H, Zhu X (2020) A survey and taxonomy of adversarial neural networks for text-to-image synthesis. Wiley Interdiscipl Rev Data Min Knowl Discov 10(4):1345

    Google Scholar 

  • Alqahtani H, Kavakli-Thorne M, Kumar G (2021) Applications of generative adversarial networks (GANs): an updated review. Arch Comput Methods Eng 28(3):525–552

    Article  MathSciNet  Google Scholar 

  • Arora S, Ge R, Liang Y, Ma T, Zhang Y (2017) Generalization and equilibrium in generative adversarial nets (GANs). http://arxiv.org/abs/1703.00573

  • Bengio S, Vinyals O, Jaitly N, Shazeer N (2015) Scheduled sampling for sequence prediction with recurrent neural networks. In: Proceedings 28th International Conference on Neural Information Processing Systems (NIPS), pp 1171–1179. MIT Press, Cambridge

  • Bissoto A, Valle E, Avila S (2019) The six fronts of the generative adversarial networks. http://arxiv.org/abs/1910.13076

  • Borji A (2019) Pros and cons of gan evaluation measures. Comput Vis Image Understand 179:41–65

    Article  Google Scholar 

  • Brocas I, Carrillo JD, Sachdeva A (2018) The path to equilibrium in sequential and simultaneous games: a mousetracking study. J Econ Theory 178:246–274

    Article  MathSciNet  MATH  Google Scholar 

  • Cai Y, Daskalakis C (2011) On minmax theorems for multiplayer games. In: Proceedings of the twenty-second annual ACM-SIAM symposium on discrete algorithms, pp 217–234

  • Cao Y-J, Jia L-L, Chen Y-X, Lin N, Yang C, Zhang B, Liu Z, Li X-X, Dai H-H (2018) Recent advances of generative adversarial networks in computer vision. IEEE Access 7:14985–15006

    Article  Google Scholar 

  • Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B, Bharath AA (2018) Generative adversarial networks: an overview. IEEE Signal Process Mag 35(1):53–65

    Article  Google Scholar 

  • Dam T, Ferdaus MM, Pratama M, Anavatti SG, Jayavelu S, Abbass H (2022) Latent preserving generative adversarial network for imbalance classification. In: 2022 IEEE International Conference on Image Processing (ICIP), pp 3712–3716

  • De Cao N, Kipf T (2018) MolGAN: an implicit generative model for small molecular graphs. http://arxiv.org/abs/1805.11973

  • Di Mattia F, Galeone P, De Simoni M, Ghelfi E (2019) A survey on GANs for anomaly detection. http://arxiv.org/abs/1906.11632

  • Durugkar I, Gemp I, Mahadevan S (2016) Generative multi-adversarial networks. http://arxiv.org/abs/1611.01673

  • Ebrahimi S, Meier F, Calandra R, Darrell T, Rohrbach M (2020) Adversarial continual learning. In: European Conference on Computer Vision, Springer, pp 386–402

  • Fan L (2020) A survey of differentially private generative adversarial networks. In: The AAAI Workshop on Privacy-Preserving Artificial Intelligence, New York

  • Fan C, Liu P (2020) Federated generative adversarial learning. http://arxiv.org/abs/2005.03793

  • Farnia F, Ozdaglar A (2020) GANs may have no Nash equilibria. http://arxiv.org/abs/2002.09124

  • Fedus W, Rosca M, Lakshminarayanan B, Dai AM, Mohamed S, Goodfellow I (2017) Many paths to equilibrium: GANs do not need to decrease a divergence at every step. http://arxiv.org/abs/1710.08446

  • Florensa C, Held D, Geng X, Abbeel P (2018) Automatic goal generation for reinforcement learning agents. In: Proceedings 35th International Conference on Machine Learning, vol. 80. Stockholm, pp 1515–1528

  • Franci B, Grammatico S (2020) Generative adversarial networks as stochastic Nash games. http://arxiv.org/abs/2010.10013

  • Gao N, Xue H, Shao W, Zhao S, Qin KK, Prabowo A, Rahaman MS, Salim FD (2020) Generative adversarial networks for spatio-temporal data: a survey. http://arxiv.org/abs/2008.08903

  • Georges-Filteau J, Cirillo E (2020) Synthetic observational health data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?

  • Ge H, Xia Y, Chen X, Berry R, Wu Y (2018) Fictitious GAN: training GANs with historical models. In: Proceedings European conference on computer vision (ECCV), Munich, pp 119–134

  • Ghosh A, Bhattacharya B, Chowdhury SBR (2016a) Handwriting profiling using generative adversarial networks. http://arxiv.org/abs/1611.08789

  • Ghosh A, Kulharia V, Namboodiri V (2016b) Message passing multi-agent GANs. http://arxiv.org/abs/1612.01294

  • Ghosh A, Kulharia V, Namboodiri VP, Torr PH, Dokania PK (2018) Multi-agent diverse generative adversarial networks. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, pp 8513–8521

  • Ghosh B, Dutta IK, Totaro M, Bayoumi M (2020) A survey on the progression and performance of generative adversarial networks. In: Proceedings of 11th ieee international conference on computing, communication and networking technologies (ICCCNT), Kharagpur, pp 1–8

  • Gonog L, Zhou Y (2019) A review: generative adversarial networks. In: Proceedings 14th IEEE conference on industrial electronics and applications (ICIEA), Xi’an, pp 505–510

  • Goodfellow I (2016) NIPS 2016 tutorial: generative adversarial networks. http://arxiv.org/abs/1701.00160

  • Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014a) Generative adversarial nets. In: Proceedings 27th International Conference on Neural Information Processing Systems (NIPS), pp 2672–2680. MIT Press, Cambridge

  • Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014b) Generative adversarial networks. http://arxiv.org/abs/1406.2661

  • Grnarova P, Levy KY, Lucchi A, Hofmann T, Krause A (2017) An online learning approach to generative adversarial networks. http://arxiv.org/abs/1706.03269

  • Guimaraes GL, Sanchez-Lengeling B, Outeiral C, Farias PLC, Aspuru-Guzik A (2017) Objective-reinforced generative adversarial networks (ORGAN) for sequence generation models. http://arxiv.org/abs/1705.10843

  • Gui J, Sun Z, Wen Y, Tao D, Ye J (2020) A review on generative adversarial networks: algorithms, theory, and applications. http://arxiv.org/abs/2001.06937

  • Hardy C, Le Merrer E, Sericola B (2019) MD-GAN: Multi-discriminator generative adversarial networks for distributed datasets. In: Proceedings IEEE International Parallel and Distributed Processing Symposium (IPDPS), Rio de Janeiro, pp 866–877

  • Hitawala S (2018) Comparative study on generative adversarial networks. http://arxiv.org/abs/1801.04271

  • Hoang Q, Nguyen TD, Le T, Phung D (2018) MGAN: training generative adversarial nets with multiple generators. In: Proceedings International Conference on Learning Representations, Vancouver

  • Hong Y, Hwang U, Yoo J, Yoon S (2019) How generative adversarial networks and their variants work: an overview. ACM Comput Surv (CSUR) 52(1):1–43

    Article  Google Scholar 

  • Hossam M, Le T, Huynh V, Papasimeon M, Phung D (2020) OptiGAN: Generative adversarial networks for goal optimized sequence generation. http://arxiv.org/abs/2004.07534

  • Hsieh Y-P, Liu C, Cevher V (2019) Finding mixed Nash equilibria of generative adversarial networks. In: Proceedings of International Conference on Machine Learning, Long Beach, pp 2810–2819

  • Jabbar A, Li X, Omar B (2020) A survey on generative adversarial networks: variants, applications, and training. http://arxiv.org/abs/2006.05132

  • Jain P, Jayaswal T (2020) Generative adversarial training and its utilization for text to image generation: a survey and analysis. J Crit Rev 7(8):1455–1463

    Google Scholar 

  • Jin Y, Wang Y, Long M, Wang J, Philip SY, Sun J (2020) A multi-player minimax game for generative adversarial networks. In: Proceedings IEEE International Conference on Multimedia and Expo (ICME), London, pp 1–6

  • Ke S, Liu W (2020) Consistency of multiagent distributed generative adversarial networks. IEEE Trans Cybern 1:1–11

    Google Scholar 

  • Kodali N, Abernethy J, Hays J, Kira Z (2017) On convergence and stability of GANs. http://arxiv.org/abs/1705.07215

  • Kumar MP, Jayagopal P (2021) Generative adversarial networks: a survey on applications and challenges. Int J Multim Inf Retrieval 10(1):1–24

    Article  Google Scholar 

  • Lee M, Seok J (2020) Regularization methods for generative adversarial networks: an overview of recent studies. http://arxiv.org/abs/2005.09165

  • Li Y, Pan Q, Wang S, Yang T, Cambria E (2018) A generative model for category text generation. Inf Sci 450:301–315

    Article  MathSciNet  Google Scholar 

  • Liang J, Tang W (2020) Sequence generative adversarial networks for wind power scenario generation. IEEE J Sel Areas Commun 38(1):110–118

    Article  MathSciNet  Google Scholar 

  • Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. http://arxiv.org/abs/1509.02971 (2015)

  • Lucic M, Kurach K, Michalski M, Gelly S, Bousquet O (2017) Are GANs created equal? A large-scale study. http://arxiv.org/abs/1711.10337

  • Lv Y, Ren X (2018) Approximate nash solutions for multiplayer mixed-zero-sum game with reinforcement learning. IEEE Trans Syst Man Cybern Syst 49(12):2739–2750

    Article  Google Scholar 

  • Mariani G, Scheidegger F, Istrate R, Bekas C, Malossi C (2018) Bagan: Data augmentation with balancing gan. http://arxiv.org/abs/1803.09655

  • Mescheder L, Nowozin S, Geiger A (2017) The numerics of GANs. In: Proceedings conference neural information processing systems, vol 30. Curran Associates Inc., Red Hook, pp 1825–1835

  • Mordido G, Yang H, Meinel C (2020) microbatchGAN: Stimulating diversity with multi-adversarial discrimination. In: Proceedings IEEE winter conference on applications of computer vision (WACV), Snowmass, pp 3050–3059

  • Mullick SS, Datta S, Das S (2019) Generative adversarial minority oversampling. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1695–1704

  • Neumann JV (1928) Zur theorie der gesellschaftsspiele. Math Ann 100(1):295–320

    Article  MathSciNet  MATH  Google Scholar 

  • Nguyen T, Le T, Vu H, Phung D (2017) Dual discriminator generative adversarial nets. In: Proceedings advances in neural information processing systems (NIPS), pp 2670–2680

  • Osborne MJ (2004) An introduction to game theory, vol 3. Oxford University Press, New York

    Google Scholar 

  • Pan Z, Yu W, Yi X, Khan A, Yuan F, Zheng Y (2019) Recent progress on generative adversarial networks (GANs): a survey. IEEE Access 7:36322–36333

    Article  Google Scholar 

  • Pan Z, Yu W, Wang B, Xie H, Sheng VS, Lei J, Kwong S (2020) Loss functions of generative adversarial networks (GANs): opportunities and challenges. IEEE Trans Emerg Top Comput Intell 4:4

    Article  Google Scholar 

  • Rasouli M, Sun T, Rajagopal R (2020) FedGAN: Federated generative adversarial networks for distributed data. http://arxiv.org/abs/2006.07228

  • Salehi P, Chalechale A, Taghizadeh M (2020) Generative adversarial networks (GANs): an overview of theoretical model, evaluation metrics, and recent developments. http://arxiv.org/abs/2005.13178

  • Sampath V, Maurtua I, Martín JJA, Gutierrez A (2021) A survey on generative adversarial networks for imbalance problems in computer vision tasks. J Big Data 8(1):27

    Article  Google Scholar 

  • Sarmad M, Lee HJ, Kim YM (2019) RL-GAN-Net: a reinforcement learning agent controlled GAN network for real-time point cloud shape completion. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, pp 5898–5907

  • Saxena D, Cao J (2020) Generative adversarial networks (GANs): challenges, solutions, and future directions. http://arxiv.org/abs/2005.00065

  • Shin S, Jeon H, Cho C, Yoon S, Kim T (2020) User mobility synthesis based on generative adversarial networks: a survey. In: Proceedings 22nd international conference on advanced communication technology (ICACT), Phoenix Park, pp 94–103

  • Shoham Y, Leyton-Brown K (2008) Multiagent systems: algorithmic, game-theoretic, and logical foundations. Cambridge University Press, Cambridge

    Book  MATH  Google Scholar 

  • Silver D, Huang A, Maddison CJ, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484–489

    Article  Google Scholar 

  • Sorin V, Barash Y, Konen E, Klang E (2020) Creating artificial images for radiology applications using generative adversarial networks (GANs): a systematic review. Acad Radiol 27:1175–1185

    Article  Google Scholar 

  • Tian Y, Wang Q, Huang Z, Li W, Dai D, Yang M, Wang J, Fink O (2020) Off-policy reinforcement learning for efficient and effective GAN architecture search. In: Proceedings European conference on computer vision (ECCV), Springer, pp 175–192

  • Tran N-T, Tran V-H, Nguyen B-N, Yang L, Cheung N-MM (2019) Self-supervised GAN: analysis and improvement with multi-class minimax game. Adv Neural Inf Process Syst (NeurIPS) 32:13253–13264

    Google Scholar 

  • Tschuchnig ME, Oostingh GJ, Gadermayr M (2020) Generative adversarial networks in digital pathology: a survey on trends and future potential. Patterns 1(6):100089

    Article  Google Scholar 

  • Wang K, Gou C, Duan Y, Lin Y, Zheng X, Wang F-Y (2017) Generative adversarial networks: introduction and outlook. IEEE/CAA J Autom Sin 4(4):588–598

    Article  MathSciNet  Google Scholar 

  • Wang Z, She Q, Ward TE (2019) Generative adversarial networks in computer vision: A survey and taxonomy. http://arxiv.org/abs/1906.01529

  • Wang L, Chen W, Yang W, Bi F, Yu FR (2020) A state-of-the-art review on image synthesis with generative adversarial networks. IEEE Access 8:63514–63537

    Article  Google Scholar 

  • Weininger D (1998) Smiles, a chemical language and information system. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci 28(1):31–36

    Article  Google Scholar 

  • Wiatrak M, Albrecht SV (2019) Stabilizing generative adversarial network training: a survey. http://arxiv.org/abs/1910.00927

  • Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8(3):229–256

    Article  MATH  Google Scholar 

  • Wu X, Xu K, Hall P (2017) A survey of image synthesis and editing with generative adversarial networks. Tsinghua Sci Technol 22(6):660–674

    Article  MATH  Google Scholar 

  • Xu J, Ren X, Lin J, Sun X (2018) Diversity-promoting GAN: a cross-entropy based generative adversarial network for diversified text generation. In: Proceedings Conference on Empirical Methods in Natural Language Processing, Brussels, pp 3940–3949 (2018)

  • Yan S, Wu F, Smith JS, Lu W, Zhang B (2018) Image captioning using adversarial networks and reinforcement learning. In: Proceedings 24th International Conference on Pattern Recognition (ICPR), Beijing, pp 248–253

  • Yi X, Walia E, Babyn P (2019) Generative adversarial network in medical imaging: a review. Med Image Anal (MEDIA) 58:101552

    Article  Google Scholar 

  • Yinka-Banjo C, Ugot O-A (2020) A review of generative adversarial networks and its application in cybersecurity. Artif Intell Rev 53(3):1721–1736

    Article  Google Scholar 

  • Yu L, Zhang W, Wang J, Yu Y (2017) SeqGAN: Sequence generative adversarial nets with policy gradient. In: Proceedings Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, pp 2852–2858

  • Zhang S-F, Zhai J-H, Luo D-S, Zhan Y, Chen J-F (2018a) Recent advance on generative adversarial networks. In: Proceedings of international conference on machine learning and cybernetics (ICMLC), Chengdu, pp 69–74

  • Zhang J, Peng Y, Yuan M (2018b) SCH-GAN: semi-supervised cross-modal hashing by generative adversarial network. IEEE Trans Cybern 50(2):489–502

    Article  Google Scholar 

  • Zhang H, Xu S, Jiao J, Xie P, Salakhutdinov R, Xing EP (2018c) Stackelberg GAN: Towards provable minimax equilibrium via multi-generator architectures. http://arxiv.org/abs/1811.08010

  • Zhao Y, Ding H, Huang H, Cheung N-M (2022) A closer look at few-shot image generation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 9140–9150

Download references

Author information

Author notes

  1. Bahar Boroomand, Mohammad Jalali, and Arman Zareian have contributed equally to this work.

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran

    Monireh Mohebbi Moghaddam, Bahar Boroomand, Mohammad Jalali, Arman Zareian, Alireza Daeijavad & Mohammad Hossein Manshaei

  2. Department of Electrical and Computer Engineering, University of Arizona, Tucson, USA

    Mohammad Hossein Manshaei & Marwan Krunz

  3. Iran University of Medical Sciences, Tehran, Iran

    Monireh Mohebbi Moghaddam

  4. Department of Computing Science, University of Alberta, Edmonton, Canada

    Bahar Boroomand

  5. Department of Computing and Software, McMaster University, Hamilton, Canada

    Alireza Daeijavad

Authors
  1. Monireh Mohebbi Moghaddam
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bahar Boroomand
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohammad Jalali
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Arman Zareian
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Alireza Daeijavad
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Mohammad Hossein Manshaei
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Marwan Krunz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammad Hossein Manshaei.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mohebbi Moghaddam, M., Boroomand, B., Jalali, M. et al. Games of GANs: game-theoretical models for generative adversarial networks. Artif Intell Rev 56, 9771–9807 (2023). https://doi.org/10.1007/s10462-023-10395-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-023-10395-6

Keywords

Search

Navigation