Inaccurate-Supervised Learning With Generative Adversarial Nets

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

4 Scopus Citations
View graph of relations

Author(s)

  • Yabin Zhang
  • Hairong Lian
  • Suyun Zhao
  • Peng Ni
  • Hong Chen
  • Cuiping Li

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)1522-1536
Journal / PublicationIEEE Transactions on Cybernetics
Volume53
Issue number3
Online published31 Aug 2021
Publication statusPublished - Mar 2023

Abstract

Inaccurate-supervised learning (ISL) is a weakly supervised learning framework for imprecise annotation, which is derived from some specific popular learning frameworks, mainly including partial label learning (PLL), partial multilabel learning (PML), and multiview PML (MVPML). While PLL, PML, and MVPML are each solved as independent models through different methods and no general framework can currently be applied to these frameworks, most existing methods for solving them were designed based on traditional machine-learning techniques, such as logistic regression, KNN, SVM, decision tree. Prior to this study, there was no single general framework that used adversarial networks to solve ISL problems. To narrow this gap, this study proposed an adversarial network structure to solve ISL problems, called ISL with generative adversarial nets (ISL-GANs). In ISL-GAN, fake samples, which are quite similar to real samples, gradually promote the Discriminator to disambiguate the noise labels of real samples. We also provide theoretical analyses for ISL-GAN in effectively handling ISL data. In this article, we propose a general framework to solve PLL, PML, and MVPML, while in the published conference version, we adopt the specific framework, which is a special case of the general one, to solve the PLL problem. Finally, the effectiveness is demonstrated through extensive experiments on various imprecise annotation learning tasks, including PLL, PML, and MVPML.

Research Area(s)

  • Annotations, Generative adversarial nets (GANs), Generators, imprecise annotation, inaccurate-supervised learning (ISL), multiview partial multilabel learning (MVPML), Noise measurement, partial label learning (PLL), partial multilabel learning (PML), Phase locked loops, Supervised learning, Task analysis, Training

Citation Format(s)

Inaccurate-Supervised Learning With Generative Adversarial Nets. / Zhang, Yabin; Lian, Hairong; Yang, Guang et al.
In: IEEE Transactions on Cybernetics, Vol. 53, No. 3, 03.2023, p. 1522-1536.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review