GAN-CL: Generative Adversarial Networks for Learning from Complementary Labels

Jiabin Liu, Hanyuan Hang, Bo Wang*, Biao Li, Huadong Wang, Yingjie Tian, Yong Shi

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

130 Downloads (Pure)


Learning from complementary labels (CLs) is a useful learning paradigm, where the CL specifies the classes that the instance does not belong to, instead of providing the ground truth as in the ordinary supervised learning scenario. In general, although it is less laborious and more efficient to collect CLs compared with ordinary labels, the less informative signal in the complementary supervision is less helpful to learn competent feature representation. Consequently, the final classifier's performance greatly deteriorates. In this article, we leverage generative adversarial networks (GANs) to derive an algorithm GAN-CL to effectively learn from CLs. In addition to the role in original GAN, the discriminator also serves as a normal classifier in GAN-CL, with the objective constructed partly with the complementary information. To further prove the effectiveness of our schema, we study the global optimality of both generator and discriminator for the GAN-CL under mild assumptions. We conduct extensive experiments on benchmark image datasets using deep models, to demonstrate the compelling improvements, compared with state-of-the-art CL learning approaches.
Original languageEnglish
Pages (from-to)236-247
Number of pages12
JournalIEEE transactions on cybernetics
Issue number1
Early online date16 Jul 2021
Publication statusPublished - Jan 2023


  • 22/2 OA procedure


Dive into the research topics of 'GAN-CL: Generative Adversarial Networks for Learning from Complementary Labels'. Together they form a unique fingerprint.

Cite this