OptiGAN: Generative Adversarial Networks for Goal Optimized Sequence Generation

Hossam, Mahmoud; Le, Trung; Huynh, Viet; Papasimeon, Michael; Phung, Dinh

doi:10.48550/arxiv.2004.07534

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stochastic game [45] Stackelberg game [46,47] Bi-affine game [48] Modified Learning Method No regret learning [10,49,50] Fictitious play [27] Federated learning [51,52] Reinforcement learning [4,[53][54][55][56][57][58][59][60][61][62][63] Modified Architecture Multiple generators, One discriminator [46,[64][65][66][67] One generator, Multiple discriminators [60,[68][69][70][71][72] Multiple generators, Multiple discriminators [51,66,73] One generator, One discriminator, One classifier [4,74] One generator, One discriminator, One RL agent [58,59,75,76]…”

Section: Modified Game Modelmentioning

confidence: 99%

“…However, in many applications, we need to generate data similar to real ones and have specific properties or attributes. Hossam et al in [62] introduced the first GANcontrolled generative model for sequences that address the diversity issue in a principled approach. The authors combine GAN and RL policy learning benefits while avoiding mode-collapse and high variance drawbacks.…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…More specifically, as the authors in [9] expressed one of the most important future direction is to improve theoretical aspects of GANs to solve problems Stackelberg GAN [46], [47], [45], MGAN [65], DDL-GAN [69], GMAN [68], MD-GAN [70], [73], DRAGAN [49], Fictitious GAN [27], [63], D2GAN [72] FID Stackelberg GAN [46], DDL-GAN [69], Microbatch GAN [71], MD-GAN [70], [74], FedGAN [51], [ Diversity-promoting GAN [56], SeqGAN [55] Classification Scores [52], [15], [60], CS-GAN [4] Others [52], ORGAN [59], OptiGAN [62] such as model collapse, non-convergence, and training difficulties. Although there have many works on the theory aspects, most of the current training strategies are based on the optimization theory, whose scope is restricted to local convergence due to the non-convexity, and the utilization of game theory techniques is still in its infancy.…”

Section: Open Problems and Future Workmentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2023

View full text Add to dashboard Cite

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 taxonomy to classify state-of-the-art solutions into three main categories: modified game models, modified architectures, Games of GANs 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.

show abstract

Section: Modified Game Modelmentioning

confidence: 99%

Section: Reinforcement Learningmentioning

confidence: 99%

Section: Open Problems and Future Workmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, in many applications, we need to generate data similar to real ones and have specific properties or attributes. Hossam et al in [62] introduce the first GAN-controlled generative model for sequences that address the diversity issue in a principled approach. The authors combine GAN and RL policy learning benefits while avoiding mode-collapse and high variance drawbacks.…”

Section: Md-ganmentioning

confidence: 99%

Game of GANs: Game-Theoretical Models for Generative Adversarial Networks

Moghadam¹,

Boroomand²,

Barzegar-Jalali³

et al. 2021

Preprint

View full text Add to dashboard Cite

Generative Adversarial Network, as a promising research direction in the AI community, recently attracts considerable attention due to its ability to generating high-quality realistic data. GANs are a competing game between two neural networks trained in an adversarial manner to reach a Nash equilibrium. Despite the improvement accomplished in GANs in the last years, there remain several issues to solve. In this way, how to tackle these issues and make advances leads to rising research interests. This paper reviews literature that leverages the game theory in GANs and addresses how game models can relieve specific generative models' challenges and improve the GAN's performance. In particular, we firstly review some preliminaries, including the basic GAN model and some game theory backgrounds. After that, we present our taxonomy to summarize the state-of-the-art solutions into three significant categories: modified game model, modified architecture, and modified learning method. The classification is based on the modifications made in the basic model by the proposed approaches from the game-theoretic perspective. We further classify each category into several subcategories. Following the proposed taxonomy, we explore the main objective of each class and review the recent work in each group. Finally, we discuss the remaining challenges in this field and present the potential future research topics.

show abstract

Games of GANs: Game-Theoretical Models for Generative Adversarial Networks

Moghadam

Boroomand

Jalali

et al. 2022

Preprint

View full text Add to dashboard Cite

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 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.

show abstract

OptiGAN: Generative Adversarial Networks for Goal Optimized Sequence Generation

Cited by 3 publications

References 0 publications

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

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

Game of GANs: Game-Theoretical Models for Generative Adversarial Networks

Games of GANs: Game-Theoretical Models for Generative Adversarial Networks

Contact Info

Product

Resources

About