Guest Editorial Special Issue on Adversarial Learning in Computational Intelligence

The seven papers in this special section focus on adversarial learning in computational intelligence. The papers aim to capture the most recent advances of adversarial learning from both theoretical and empirical perspectives. Moreover, it attempts to present its novel applications to other domains beyond image generation. Adversarial learning has attracted tremendous attention in the community of machine learning over the past few years. It normally integrates two components that contest with each other in a two-player zero-sum game. Since its birth in 2014, adversarial learning has been widely applied to not only the generation of realistic images, but also many other research topics, such as data augmentation, domain adaptation, and adversarial attack, often leading to appealing performance. However, we have just witnessed the early rise of this technique, and still confront many challenges, for example, the mode collapse problem, and the interpretability of its results and failures. Computational Intelligence (CI) technologies are expected to provide efficient solutions to deal with the raised challenges. Moreover, most of the previous adversarial-learning studies are largely limited in addressing static images or feature vectors. It still remains largely an open question of how adversarial learning performs for other complex and temporally variational signals or modalities, such as speech and text.