Object-Oriented Learning (OOL): Perception, Representation, and Reasoning
International Conference on Machine Learning (ICML)
Friday July 17, 2020, Virtual Workshop
The video will become available after 1st August 2020 in accordance with the ICML2020 Code of Conduct.
Groups of entities are naturally represented as sets, 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 collections, which has to be accounted for in loss computation. We therefore introduce GAST - a GAN for sets 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.