BourGAN: Generative Networks with Metric Embeddings

This paper addresses the mode collapse for generative adversarial networks (GANs). We view modes as a geometric structure of data distribution in a metric space. Under this geometric lens, we embed subsamples of the dataset from an arbitrary metric space into the l2 space, while preserving their pairwise distance distribution. Not only does this metric embedding determine the dimensionality of the latent space automatically, it also enables us to construct a mixture of Gaussians to draw latent space random vectors. We use the Gaussian mixture model in tandem with a simple augmentation of the objective function to train GANs. Every major step of our method is supported by theoretical analysis, and our experiments on real and synthetic data confirm that the generator is able to produce samples spreading over most of the modes while avoiding unwanted samples, outperforming several recent GAN variants on a number of metrics and offering new features.

[1]  Matthias Bethge,et al.  A note on the evaluation of generative models , 2015, ICLR.

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

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

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

[5]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[6]  Ali Borji,et al.  Pros and Cons of GAN Evaluation Measures , 2018, Comput. Vis. Image Underst..

[7]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[8]  Alexandros G. Dimakis,et al.  AmbientGAN: Generative models from lossy measurements , 2018, ICLR.

[9]  J. Matousek.  Embedding Finite Metric Spaces into Normed Spaces , 2002 .

[10]  W. B. Johnson,et al.  Extensions of Lipschitz mappings into Hilbert space , 1984 .

[11]  Sebastian Nowozin,et al.  f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization , 2016, NIPS.

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

[13]  Nathan Linial,et al.  The geometry of graphs and some of its algorithmic applications , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

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

[15]  Alexandros G. Dimakis,et al.  Compressed Sensing using Generative Models , 2017, ICML.

[16]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[17]  Nicolas Courty,et al.  Learning Wasserstein Embeddings , 2017, ICLR.

[18]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[19]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[22]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[23]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Bernhard Schölkopf,et al.  AdaGAN: Boosting Generative Models , 2017, NIPS.

[25]  Andrew Gordon Wilson,et al.  Bayesian GAN , 2017, NIPS.

[26]  Jirí Matousek,et al.  Low-Distortion Embeddings of Finite Metric Spaces , 2004, Handbook of Discrete and Computational Geometry, 2nd Ed..

[27]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[29]  Yiming Yang,et al.  MMD GAN: Towards Deeper Understanding of Moment Matching Network , 2017, NIPS.

[30]  Yoshua Bengio,et al.  Mode Regularized Generative Adversarial Networks , 2016, ICLR.

[31]  F. Pukelsheim.  The Three Sigma Rule , 1994 .

[32]  J. Bourgain.  On lipschitz embedding of finite metric spaces in Hilbert space , 1985 .

[33]  David Lopez-Paz,et al.  Optimizing the Latent Space of Generative Networks , 2017, ICML.

[34]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[35]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[36]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

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

[38]  Antonio Torralba,et al.  Generating Videos with Scene Dynamics , 2016, NIPS.

[39]  Frank Thomson Leighton,et al.  An approximate max-flow min-cut theorem for uniform multicommodity flow problems with applications to approximation algorithms , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

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

[41]  Yingyu Liang,et al.  Generalization and Equilibrium in Generative Adversarial Nets (GANs) , 2017, ICML.

[42]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[43]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[44]  Jiajun Wu,et al.  Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , 2016, NIPS.

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

[46]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[47]  J. Zico Kolter,et al.  Gradient descent GAN optimization is locally stable , 2017, NIPS.

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

[49]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

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