LogicGAN: Logic-guided Generative Adversarial Networks

02/24/2020
by   Laura Graves, et al.
0

Generative Adversarial Networks (GANs) are a revolutionary class of Deep Neural Networks (DNNs) that have been successfully used to generate realistic images, music, text, and other data. However, it is well known that GAN training can be notoriously resource-intensive and presents many challenges. Further, a potential weakness in GANs is that discriminator DNNs typically provide only one value (loss) of corrective feedback to generator DNNs (namely, the discriminator's assessment of the generated example). By contrast, we propose a new class of GAN we refer to as LogicGAN, that leverages recent advances in (logic-based) explainable AI (xAI) systems to provide a "richer" form of corrective feedback from discriminators to generators. Specifically, we modify the gradient descent process using xAI systems that specify the reason as to why the discriminator made the classification it did, thus providing the richer corrective feedback that helps the generator to better fool the discriminator. Using our approach, we show that LogicGANs learn much faster on MNIST data, achieving an improvement in data efficiency of 45 12.73 quality as measured by Fréchet Inception Distance. Further, we argue that LogicGAN enables users greater control over how models learn than standard GAN systems.

READ FULL TEXT

page 5

page 6

research
10/30/2019

Investigating Under and Overfitting in Wasserstein Generative Adversarial Networks

We investigate under and overfitting in Generative Adversarial Networks ...
research
10/27/2021

Fuzzy Generative Adversarial Networks

Generative Adversarial Networks (GANs) are well-known tools for data gen...
research
07/12/2022

Face editing with GAN – A Review

In recent years, Generative Adversarial Networks (GANs) have become a ho...
research
10/06/2020

Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks

Machine learning predictors have been increasingly applied in production...
research
01/19/2022

A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis

In biomedical image analysis, the applicability of deep learning methods...
research
01/17/2020

Interpreting Galaxy Deblender GAN from the Discriminator's Perspective

Generative adversarial networks (GANs) are well known for their unsuperv...
research
02/28/2023

Double Dynamic Sparse Training for GANs

The past decade has witnessed a drastic increase in modern deep neural n...

Please sign up or login with your details

Forgot password? Click here to reset