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

Abstract

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.

arXiv comment18 pages, 5 Tables, 6 Figures, Review paper

References in corpus (29)

• Continuous control with deep reinforcement learning
• Generative Adversarial Networks: An Overview
• Generative Adversarial Network in Medical Imaging: A Review
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• MolGAN: An implicit generative model for small molecular graphs
• How Generative Adversarial Networks and Their Variants Work: An Overview
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• On Convergence and Stability of GANs
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• The Numerics of GANs
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• A Survey on GANs for Anomaly Detection
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• Stabilizing Generative Adversarial Networks: A Survey
• Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• FedGAN: Federated Generative Adversarial Networks for Distributed Data
• GANs May Have No Nash Equilibria
• Comparative Study on Generative Adversarial Networks
• Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies
• Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
• Message Passing Multi-Agent GANs
• The Six Fronts of the Generative Adversarial Networks
• An Online Learning Approach to Generative Adversarial Networks
• Synthetic Observational Health Data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?
• Federated Generative Adversarial Learning