Mixing Up Real Samples and Adversarial Samples for Semi-Supervised Learning

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with host publication)peer-review

3 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2020 International Joint Conference on Neural Networks (IJCNN) - 2020 Conference Proceedings
PublisherIEEE
ISBN (Electronic)978-1-7281-6926-2
Publication statusPublished - Jul 2020

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Conference

Title2020 International Joint Conference on Neural Networks (IJCNN 2020)
LocationVirtual
PlaceUnited Kingdom
CityGlasgow
Period19 - 24 July 2020

Abstract

Consistency regularization methods have shown great success in semi-supervised learning tasks. Most existing methods focus on either the local neighborhood or in-between neighborhood of training samples to enforce the consistency constraint. In this paper, we propose a novel generalized framework called Adversarial Mixup (AdvMixup), which unifies the local and in-between neighborhood approaches by defining a virtual data distribution along the paths between the training samples and adversarial samples. Experimental results on both synthetic data and benchmark datasets exhibit that our AdvMixup can achieve better performance and robustness than state-of-the-art methods for semi-supervised learning.

Research Area(s)

  • adversarial samples, mixup, semi-supervised learning

Citation Format(s)

Mixing Up Real Samples and Adversarial Samples for Semi-Supervised Learning. / Ma, Yun; Mao, Xudong; Chen, Yangbin et al.
2020 International Joint Conference on Neural Networks (IJCNN) - 2020 Conference Proceedings. IEEE, 2020. 9207038 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with host publication)peer-review