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

TL;DR

This paper reviews how game theory models can address challenges in GANs, classifying recent solutions into three categories and discussing their objectives, effectiveness, and future research directions.

Contribution

It provides a comprehensive taxonomy of game-theoretic approaches to improve GAN performance, highlighting recent advancements and remaining challenges.

Findings

Classified solutions into modified game models, architectures, and learning methods.

Analyzed objectives and effectiveness of each category.

Identified future research directions in game-theoretic GANs.

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.