Learning from Label Proportions with Generative Adversarial Networks
Jiabin Liu, Bo Wang, Zhiquan Qi, YingJie Tian, Yong Shi
Abstract
In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level proportional information in labels is available. Endowed with end-to-end structure, LLP-GAN performs approximation in the light of an adversarial learning mechanism, without imposing restricted assumptions on distribution. Accordingly, we can directly induce the final instance-level classifier upon the discriminator. Under mild assumptions, we give the explicit generative representation and prove the global optimality for LLP-GAN. Additionally, compared with existing methods, our work empowers LLP solver with capable scalability inheriting from deep models. Several experiments on benchmark datasets demonstrate vivid advantages of the proposed approach.
BibTeX
@inproceedings{NEURIPS2019_4fc84805,
author = {Liu, Jiabin and Wang, Bo and Qi, Zhiquan and Tian, YingJie and Shi, Yong},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Learning from Label Proportions with Generative Adversarial Networks},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/4fc848051e4459b8a6afeb210c3664ec-Paper.pdf},
volume = {32},
year = {2019}
}