Belief propagation generative adversarial networks

Wang, Sifan

Permalink

https://hdl.handle.net/2142/98120 Copy

Description

Title

Belief propagation generative adversarial networks

Author(s)

Wang, Sifan

Issue Date

2017-07-20

Director of Research (if dissertation) or Advisor (if thesis)

Schwing, Alexander

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Date of Ingest

2017-09-29T16:37:57Z

Keyword(s)

• Generative adversarial network
• Belief propagation
• Graphical model
• Penalty method

Abstract

Generative adversarial networks (GANs) are a class of generative models based on a minimax game. They have led to significant improvement in the field of unsupervised learning, especially image generation. However, most works in GANs are based on learning the distribution of the input dataset through a multi-layer neural network which does not explicitly model the structure of the input variables. This may work well in large and less noisy datasets, with the expectation that the learning procedure is able to assign relatively small weights to the occasional noise through averaging of many inputs. However, this approach potentially suffers when the input size is limited or noisy, resulting in reduced quality of generated samples by picking up spurious structures. In this thesis we propose a technique to model the structure of the variable interactions by incorporating graphical models in the generative adversarial network. The proposed framework produces samples by passing random inputs through a neural network to construct the local potentials in the graphical model; performing probabilistic inference in this graphical model then yields the marginal distribution. Message passing based on discrete variables keeps a table of local potential values, the size of which could be too big for natural images. We present a solution based on continuous variables with unary and pairwise Gaussian potentials, and perform probabilistic inference using loopy belief propagation on continuous Markov random fields. Experiments on the MNIST dataset show that our model is able to outperform vanilla GANs with more than two iterations of belief propagation.

Graduation Semester

2017-08

Type of Resource

text

Permalink

http://hdl.handle.net/2142/98120

Copyright and License Information

Copyright 2017 Sifan Wang

Owning Collections