Generative Adversarial Set Transformers

Karl Stelzner, Kristian Kerstin, Adam R. Kosiorek

Abstract: Generative Adversarial Set TransformersKarl Stelzner1Kristian Kersting1Adam R. Kosiorek2AbstractGroups of entities are naturally represented assets, but generative models usually treat them as independent from each other or as sequences. This either over-simplifies the problem or imposes an order to the otherwise unordered col-lections, which has to be accounted for in loss computation. We, therefore, introduce generative adversarial set transformer(GAST)—aGANforsets capable of generating variable-sized sets in a permutation-equivariant manner, while accounting for dependencies between set elements. It avoids the problem of formulating a distance metric between sets by using a permutation-invariant discriminator. When evaluated on a dataset of regular polygons and on MNIST point clouds, GAST outperforms graph-convolution-based GANs in sample fidelity, while showing good generalization to novel set sizes