Semi-supervised Learning Using Generative Adversarial Networks

Chuan Yu Chang, Tzu Yang Chen, Pau-Choo Chung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Machine learning is a powerful tool in many applications, but the most difficult process in machine learning is the collection of data and the labeling of data. Unsupervised and semi-supervised learning has thus become an important issue. In this paper, we introduce a semi-supervised learning approach which using generative adversarial networks to generate training samples. Those imitated samples were involved in training set to train the classifier, this can improve the stability and robustness of the classifier models. To demonstrate the performance of the proposed framework, four benchmarks including Iris, MNIST, CIFAR-10, and SVHN datasets were evaluated. The experimental results show that even in a small amount of training data, the proposed framework can predict more accurately than the existing methods.

Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
EditorsSuresh Sundaram
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages892-896
Number of pages5
ISBN (Electronic)9781538692769
DOIs
Publication statusPublished - 2019 Jan 28
Event8th IEEE Symposium Series on Computational Intelligence, SSCI 2018 - Bangalore, India
Duration: 2018 Nov 182018 Nov 21

Publication series

NameProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

Conference

Conference8th IEEE Symposium Series on Computational Intelligence, SSCI 2018
CountryIndia
CityBangalore
Period18-11-1818-11-21

Fingerprint

Semi-supervised Learning
Supervised learning
Learning systems
Classifiers
Machine Learning
Classifier
Labeling
Iris
Training Samples
Benchmark
Robustness
Predict
Experimental Results
Demonstrate
Framework
Training
Model

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Theoretical Computer Science

Cite this

Chang, C. Y., Chen, T. Y., & Chung, P-C. (2019). Semi-supervised Learning Using Generative Adversarial Networks. In S. Sundaram (Ed.), Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018 (pp. 892-896). [8628663] (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI.2018.8628663
Chang, Chuan Yu ; Chen, Tzu Yang ; Chung, Pau-Choo. / Semi-supervised Learning Using Generative Adversarial Networks. Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. editor / Suresh Sundaram. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 892-896 (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018).
@inproceedings{ebbd441d128741c3b9d3aa087c4685a1,
title = "Semi-supervised Learning Using Generative Adversarial Networks",
abstract = "Machine learning is a powerful tool in many applications, but the most difficult process in machine learning is the collection of data and the labeling of data. Unsupervised and semi-supervised learning has thus become an important issue. In this paper, we introduce a semi-supervised learning approach which using generative adversarial networks to generate training samples. Those imitated samples were involved in training set to train the classifier, this can improve the stability and robustness of the classifier models. To demonstrate the performance of the proposed framework, four benchmarks including Iris, MNIST, CIFAR-10, and SVHN datasets were evaluated. The experimental results show that even in a small amount of training data, the proposed framework can predict more accurately than the existing methods.",
author = "Chang, {Chuan Yu} and Chen, {Tzu Yang} and Pau-Choo Chung",
year = "2019",
month = "1",
day = "28",
doi = "10.1109/SSCI.2018.8628663",
language = "English",
series = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "892--896",
editor = "Suresh Sundaram",
booktitle = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",
address = "United States",

}

Chang, CY, Chen, TY & Chung, P-C 2019, Semi-supervised Learning Using Generative Adversarial Networks. in S Sundaram (ed.), Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018., 8628663, Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018, Institute of Electrical and Electronics Engineers Inc., pp. 892-896, 8th IEEE Symposium Series on Computational Intelligence, SSCI 2018, Bangalore, India, 18-11-18. https://doi.org/10.1109/SSCI.2018.8628663

Semi-supervised Learning Using Generative Adversarial Networks. / Chang, Chuan Yu; Chen, Tzu Yang; Chung, Pau-Choo.

Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. ed. / Suresh Sundaram. Institute of Electrical and Electronics Engineers Inc., 2019. p. 892-896 8628663 (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Semi-supervised Learning Using Generative Adversarial Networks

AU - Chang, Chuan Yu

AU - Chen, Tzu Yang

AU - Chung, Pau-Choo

PY - 2019/1/28

Y1 - 2019/1/28

N2 - Machine learning is a powerful tool in many applications, but the most difficult process in machine learning is the collection of data and the labeling of data. Unsupervised and semi-supervised learning has thus become an important issue. In this paper, we introduce a semi-supervised learning approach which using generative adversarial networks to generate training samples. Those imitated samples were involved in training set to train the classifier, this can improve the stability and robustness of the classifier models. To demonstrate the performance of the proposed framework, four benchmarks including Iris, MNIST, CIFAR-10, and SVHN datasets were evaluated. The experimental results show that even in a small amount of training data, the proposed framework can predict more accurately than the existing methods.

AB - Machine learning is a powerful tool in many applications, but the most difficult process in machine learning is the collection of data and the labeling of data. Unsupervised and semi-supervised learning has thus become an important issue. In this paper, we introduce a semi-supervised learning approach which using generative adversarial networks to generate training samples. Those imitated samples were involved in training set to train the classifier, this can improve the stability and robustness of the classifier models. To demonstrate the performance of the proposed framework, four benchmarks including Iris, MNIST, CIFAR-10, and SVHN datasets were evaluated. The experimental results show that even in a small amount of training data, the proposed framework can predict more accurately than the existing methods.

UR - http://www.scopus.com/inward/record.url?scp=85062774164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062774164&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2018.8628663

DO - 10.1109/SSCI.2018.8628663

M3 - Conference contribution

T3 - Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

SP - 892

EP - 896

BT - Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

A2 - Sundaram, Suresh

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chang CY, Chen TY, Chung P-C. Semi-supervised Learning Using Generative Adversarial Networks. In Sundaram S, editor, Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 892-896. 8628663. (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018). https://doi.org/10.1109/SSCI.2018.8628663