• Home
  • Search
  • Data Augment in Imbalanced Learning Based on Generative Adversarial Networks
  • Cite Icon5
  • https://doi.org/10.1007/978-3-030-36808-1_3Copy DOI Icon

Data Augment in Imbalanced Learning Based on Generative Adversarial Networks

  • Jan 1, 2019
  • Zhuocheng Zhou +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Imbalanced learning is a traditional problem in machine learning and widely occurs in many applications. Most of the methods apply simple geometric transformation for data augment to imbalanced datasets. Due to those methods learn from local information, they might generate noisy samples in the dataset with high dimension and special complexity. To solve the problem, we propose an improved Generative Adversarial Networks with modification function (GAN-MF) to approximate the true distribution of the minority class of the dataset. The model could generate data from an overall perspective to overcome the limitation of the simple geometric transformation. The performance of GAN-MF is compared against multiple standard oversampling algorithms on several imbalanced learning tasks. Experiments demonstrate that the model has an improvement in data augment for imbalanced learning.

Similar Papers
  • Conference Article
  • Citations4

Laser Engraver Control System based on Reinforcement Adversarial Learning

  • Sep 01, 2019
  • Evgeny Nikolaev
  • Research Article
  • Citations21

Adaptive data augmentation for supervised learning over missing data

  • Mar 01, 2021
  • Proceedings of the VLDB Endowment
  • Tongyu Liu +5
  • Research Article

Adaptive Margin Broad Learning System for Imbalanced Data Classification

  • May 03, 2026
  • International Journal of Creative and Open Research in Engineering and Management
  • Bhagat Sing Raghuwanshi Bhagat Sing Raghuwanshi +1
  • Research Article
  • Citations10

Minority manifold regularization by stacked auto-encoder for imbalanced learning

  • Nov 17, 2020
  • Expert Systems with Applications
  • Nima Farajian +1
  • Conference Article
  • Citations2

Big Data Analytics

  • Aug 10, 2015
  • Tianbao Yang +2
  • Research Article

A GAN-based hybrid approach for addressing class imbalance in machine learning

  • Jan 01, 2025
  • Computer Science and Information Systems
  • Dae-Kyoo Kim +1
  • Research Article
  • Citations373

Alignment of fibroblasts on grooved surfaces described by a simple geometric transformation.

  • Jul 01, 1986
  • Journal of Cell Science
  • G A Dunn +1
  • Research Article
  • Citations100

A General Framework for Decentralized Optimization With First-Order Methods

  • Sep 12, 2020
  • Proceedings of the IEEE
  • Ran Xin +3
  • Research Article
  • Citations30

Generative Adversarial Network with Multi-branch Discriminator for imbalanced cross-species image-to-image translation

  • Apr 24, 2021
  • Neural Networks
  • Ziqiang Zheng +5
  • Conference Article
  • Citations14

Experimental Assessment of the Performance of Data Augmentation with Generative Adversarial Networks in the Image Classification Problem

  • Oct 01, 2019
  • Ozge Oztimur Karadag +1
  • Research Article
  • Citations2

Advancing Software Project Effort Estimation: Leveraging a NIVIM for Enhanced Preprocessing

  • Dec 18, 2024
  • Journal of Software: Evolution and Process
  • Syed Sarmad Ali +4
  • Supplementary Content
  • Citations4

Solving Machine Learning Problems with Biological Principles

  • Aug 04, 2020
  • heiDOK (Heidelberg University)
  • Luziwei Leng
  • Book Chapter
  • Citations2

Time Series Forecasting Using Support Vector Machines

  • Jul 26, 2021
  • V Kumar +1
  • Conference Article
  • Citations8

Synthetic Class Specific Bangla Handwritten Character Generation Using Conditional Generative Adversarial Networks

  • Sep 01, 2019
  • Zinnia Khan Nishat +1
  • Book Chapter
  • Citations3

Retention Prediction in the Gaming Industry: Fuzzy Machine Learning Approach

  • Aug 25, 2022
  • Ahmet Tezcan Tekin +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.