Generative Adversarial Structured Networks

We propose a technique that combines generative adversarial networks with probabilistic graphical models to explicitly model dependencies in structured distributions. Generative adversarial structured networks (GASNs) produce samples by passing random inputs through a neural network to construct the potentials of a graphical model; maximum a-posteriori inference in this graphical model then yields a sample. To train a GASN, one must differentiate a bi-level optimization, which is non-trivial. We present a solution based on “smoothing” the generator, and propose two methods for obtaining the smoothed gradient. We show preliminary experimental results, demonstrating that training GASNs is feasible.

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

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

[3]  Marc Pollefeys,et al.  Distributed message passing for large scale graphical models , 2011, CVPR 2011.

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

[5]  Richard S. Zemel,et al.  Generative Moment Matching Networks , 2015, ICML.

[6]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[7]  Marc Pollefeys,et al.  Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins , 2012, NIPS.

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

[9]  Ofer Meshi,et al.  Convexifying the Bethe Free Energy , 2009, UAI.

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

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

[12]  Michael I. Jordan.  Graphical Models , 2003 .

[13]  Anoop Cherian,et al.  On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization , 2016, ArXiv.

[14]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.

[15]  Yair Weiss,et al.  MAP Estimation, Linear Programming and Belief Propagation with Convex Free Energies , 2007, UAI.

[16]  Hui Jiang,et al.  Generating images with recurrent adversarial networks , 2016, ArXiv.

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

[18]  Tamir Hazan,et al.  Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies , 2008, UAI.