Learning from Label Proportions with Generative Adversarial Networks
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.
Cite
@article{arxiv.1909.02180,
title = {Learning from Label Proportions with Generative Adversarial Networks},
author = {Jiabin Liu and Bo Wang and Zhiquan Qi and Yingjie Tian and Yong Shi},
journal= {arXiv preprint arXiv:1909.02180},
year = {2019}
}
Comments
Accepted as a conference paper at NeurIPS 2019