Adversarial Evolutionary Learning with Distributed Spatial Coevolution

Adversarial Evolutionary Learning (AEL) is concerned with competing adversaries that are adapting over time. This competition can be defined as a minimization–maximization problem. Different methods exist to model the search for solutions to this problem, such as the Competitive Coevolutionary Algorithm, Multi-agent Reinforcement LearningReinforcement Learning, Adversarial Machine Learning, and Evolutionary Game Theory. This chapter introduces an overview of AEL. We focus on spatially distributed competitive coevolutionCompetitive coevolution for adversarial evolutionary learning to deal with the Generative Adversarial Networks (GANs)Generative Adversarial Network (GAN) training challenges. A population of multiple individual solutions, parameterized artificial neural networks (ANN), provides diversityDiversity to the gradient-based GAN learning and increases the robustness of the GAN training. The computational complexity is reduced by using a spatial topology that decreases the number of evaluations and facilitates scalability. In addition, the topology enables diverse hyper-parameters, objectives, search operators, and data. We present a design and an implementation of an AEL system with spatial competitive coevolutionCompetitive coevolution and gradient-based adversarial learning. We demonstrate how the increase in diversityDiversity improves the performance of generative learning tasks on image data. Moreover, the distributed population in AEL can help overcome some hardware limitations for ANN architectures.