SetGAN: Improving the stability and diversity of generative models through a permutation invariant architecture

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.

[1]  Barnabás Póczos,et al.  Deep Learning with Sets and Point Clouds , 2016, ICLR.

[2]  Yair Weiss,et al.  On GANs and GMMs , 2018, NeurIPS.

[3]  Yann LeCun,et al.  Energy-based Generative Adversarial Networks , 2016, ICLR.

[4]  David Pfau,et al.  Unrolled Generative Adversarial Networks , 2016, ICLR.

[5]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[6]  Yi Zhang,et al.  Do GANs actually learn the distribution? An empirical study , 2017, ArXiv.

[7]  Nathaniel Virgo,et al.  Permutation-equivariant neural networks applied to dynamics prediction , 2016, ArXiv.

[8]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[9]  Charles A. Sutton,et al.  VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning , 2017, NIPS.

[10]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[11]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[13]  M. Roederer,et al.  Probability binning comparison: a metric for quantitating univariate distribution differences. , 2001, Cytometry.

[14]  Ashish Khetan,et al.  PacGAN: The Power of Two Samples in Generative Adversarial Networks , 2017, IEEE Journal on Selected Areas in Information Theory.

[15]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.

[16]  Michael Felsberg,et al.  Soft Histograms for Belief Propagation , 2006 .

[17]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[18]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[19]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[20]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[21]  Alexander J. Smola,et al.  Deep Sets , 2017, 1703.06114.

[22]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.