arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.06976cs.LGcs.AIcs.GT
收藏

GANs的博弈:生成对抗网络的博弈理论模型

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

Isfahan University of Technology(伊斯法罕理工大学);University of Arizona(亚利桑那大学)

Monireh Mohebbi Moghadam, Bahar Boroomand, Mohammad Jalali, Arman Zareian, Alireza DaeiJavad, Mohammad Hossein Manshaei, Marwan Krunz

摘要:

生成对抗网络(GANs)最近在AI社区引起了相当大的关注,因为它能够生成与真实数据具有显著统计相似性的高质量数据。从根本上说,GAN是两个神经网络之间的博弈,它们以对抗的方式训练,以达到零和纳什均衡。尽管GANs在过去几年中取得了进步,但仍有一些问题有待解决。本文回顾了有关GANs博弈论方面的文献,并讨论了博弈论模型如何解决生成模型的特定挑战并提高GAN的性能。我们首先介绍了一些基本知识,包括基本的GAN模型和一些博弈论背景。然后,我们提出了分类法,将最先进的解决方案分为三个主要类别:修改后的游戏模型,修改后的架构和修改后的学习方法。分类是基于修改的基本GAN模型提出的博弈论方法在文献中。然后,我们探讨每个类别的目标,并讨论每个类别的近期作品。最后,我们讨论了在这一领域仍然存在的挑战,并提出未来的研究方向。

英文摘要:

Generative Adversarial Networks (GANs) have recently attracted considerable attention in the AI community due to its 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 model 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 category. Finally, we discuss the remaining challenges in this field and present future research directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑