Differential-Critic GAN: Generating What You Want by a Cue of Preferences

by   Yinghua Yao, et al.

This paper proposes Differential-Critic Generative Adversarial Network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset possesses the desired property, which generates desired data that meets user's expectations and can assist in designing biological products with desired properties. Existing approaches select the desired samples first and train regular GANs on the selected samples to derive the user-desired data distribution. However, the selection of the desired data relies on an expert criterion and supervision over the entire dataset. DiCGAN introduces a differential critic that can learn the preference direction from the pairwise preferences, which is amateur knowledge and can be defined on part of the training data. The resultant critic guides the generation of the desired data instead of the whole data. Specifically, apart from the Wasserstein GAN loss, a ranking loss of the pairwise preferences is defined over the critic. It endows the difference of critic values between each pair of samples with the pairwise preference relation. The higher critic value indicates that the sample is preferred by the user. Thus training the generative model for higher critic values encourages the generation of user-preferred samples. Extensive experiments show that our DiCGAN achieves state-of-the-art performance in learning the user-desired data distributions, especially in the cases of insufficient desired data and limited supervision.



There are no comments yet.


page 1

page 9

page 11

page 12


Demystifying MMD GANs

We investigate the training and performance of generative adversarial ne...

Primal-Dual Wasserstein GAN

We introduce Primal-Dual Wasserstein GAN, a new learning algorithm for b...

CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users

A major drawback of cross-network recommender solutions is that they can...

ExGAN: Adversarial Generation of Extreme Samples

Mitigating the risk arising from extreme events is a fundamental goal wi...

Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting

Generative adversarial networks (GANs) are an exciting alternative to al...

Fisher GAN

Generative Adversarial Networks (GANs) are powerful models for learning ...

Reciprocal Adversarial Learning via Characteristic Functions

Generative adversarial nets (GANs) have become a preferred tool for acco...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.