SetGAN: Improving the stability and diversity of generative models through a permutation invariant architecture
arXiv:1907.00109
Abstract
Generative adversarial networks (GANs) have proven effective in modeling distributions of high-dimensional data. However, their training instability is a well-known hindrance to convergence, which results in practical challenges in their applications to novel data. Furthermore, even when convergence is reached, GANs can be affected by mode collapse, a phenomenon for which the generator learns to model only a small part of the target distribution, disregarding the vast majority of the data manifold or distribution. This paper addresses these challenges by introducing SetGAN, an adversarial architecture that processes sets of generated and real samples, and discriminates between the origins of these sets (i.e., training versus generated data) in a flexible, permutation invariant manner. We also propose a new metric to quantitatively evaluate GANs that does not require previous knowledge of the application, apart from the data itself. Using the new metric, in conjunction with the state-of-the-art evaluation methods, we show that the proposed architecture, when compared with GAN variants stemming from similar strategies, produces more accurate models of the input data in a way that is also less sensitive to hyperparameter settings.
References in corpus (11)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Energy-based Generative Adversarial Network
- Adversarially Learned Inference
- VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- Unrolled Generative Adversarial Networks
- Do GANs actually learn the distribution? An empirical study
- On GANs and GMMs
- Permutation-equivariant neural networks applied to dynamics prediction
- Deep Learning with Sets and Point Clouds