Annealing Genetic GAN for Imbalanced Web Data Learning

Jingyu Hao, Chengjia Wang, Guang Yang, Zhifan Gao, Jinglin Zhang*, Heye Zhang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Class imbalance is one of the most basic and important problems of web data. The key to overcoming the class imbalance problems is to increase the effective instances of the minority, that is, data augmentation. Generative Adversarial Networks (GANs), which have recently been successfully applied in the field of image generation, can be used for data augmentation because they can learn the data distribution given ample training data instances and generate more data. However, learning the distributions from the imbalanced data can make GANs easily get stuck in a local optimum. In this work, we propose a new training strategy called Annealing Genetic GAN (AGGAN), which incorporates simulated annealing genetic algorithm into the training process of GANs. And this can help GANs avoid the local optimum trapping problem, which easily occurs when the training set is imbalanced. Unlike existing GANs, which use a fixed adversarial learning objective alternately training a generator, we use multiple adversarial learning objectives to train a set of generators and use the Metropolis criterion in simulated annealing to decide whether the generator should update. More specifically, the Metropolis criterion accepts worse solutions with a certain probability, so it can make our AGGAN escape from the local optimum and find a better solution. Theory and mathematical analysis provide strong theoretical support for the proposed training strategy. And experiments on several datasets demonstrate that AGGAN achieves convincing ability to solve the class imbalanced problem and reduces the training problems inherent in existing GANs.

Original languageEnglish
Pages (from-to)1164-1174
Number of pages11
JournalIEEE Transactions on Multimedia
Volume24
Early online date15 Oct 2021
DOIs
Publication statusPublished - 2022

Keywords

  • Class imbalance problem
  • data augmentation
  • evolutionary computation
  • Generative adversarial networks

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Annealing Genetic GAN for Imbalanced Web Data Learning'. Together they form a unique fingerprint.

Cite this