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

Yao, Yinghua1,2; Pan, Yuangang3; Tsang, Ivor W.2,3; Yao, Xin1,4,5

2022-08-01

10.1109/TNNLS.2022.3197313

IEEE Transactions on Neural Networks and Learning Systems   Impact Factor & Quartile

2162-237X

2162-2388

This article 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. DiCGAN generates desired data that meet the 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 global knowledge and supervision over the entire dataset. DiCGAN introduces a differential critic that learns from pairwise preferences, which are local knowledge and can be defined on a part of training data. The critic is built by defining an additional ranking loss over the Wasserstein GAN's critic. It endows the difference of critic values between each pair of samples with the user preference and guides the generation of the desired data instead of the whole data. For a more efficient solution to ensure data quality, we further reformulate DiCGAN as a constrained optimization problem, based on which we theoretically prove the convergence of our DiCGAN. Extensive experiments on a diverse set of datasets with various applications demonstrate 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.

Generative adversarial networks Training data Training Generators Robots Labeling Knowledge engineering Desired data generation generative adversarial network (GAN) pairwise ranking user preference

SCI ; EI

English

First

Program for Guangdong Introducing Innovative and Entrepreneurial Teams[2017ZT07X386] ; Shenzhen Science and Technology Program[KQTD2016112514355531] ; Program for Guangdong Provincial Key Laboratory[2020B121201001] ; Australian Research Council[DP200101328]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic

WOS:000849243100001

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20223712722921

Computer vision ; Constrained optimization ; Personnel training ; Product design

Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Vision:741.2 ; Personnel:912.4 ; Production Engineering:913.1 ; Systems Science:961

Web of Science

1.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Guangdong Key Lab Brain Inspired Intelligent Comp, Shenzhen 518055, Peoples R China
2.Univ Technol Sydney, Australian Artificial Intelligence Inst, Ultimo, NSW 2007, Australia
3.A STAR Ctr Frontier AI Res, Singapore 138632, Singapore
4.Southern Univ Sci & Technol, Res Inst Trustworthy Autonomous Syst RITAS, Shenzhen 518055, Peoples R China
5.Univ Birmingham, Sch Comp Sci, Birmingham B15 2TT, W Midlands, England

Yao, Yinghua,Pan, Yuangang,Tsang, Ivor W.,et al. Differential-Critic GAN: Generating What You Want by a Cue of Preferences[J]. IEEE Transactions on Neural Networks and Learning Systems,2022,PP(99):1-15.

Yao, Yinghua,Pan, Yuangang,Tsang, Ivor W.,&Yao, Xin.(2022).Differential-Critic GAN: Generating What You Want by a Cue of Preferences.IEEE Transactions on Neural Networks and Learning Systems,PP(99),1-15.

Yao, Yinghua,et al."Differential-Critic GAN: Generating What You Want by a Cue of Preferences".IEEE Transactions on Neural Networks and Learning Systems PP.99(2022):1-15.