Learning from Label Proportions with Generative Adversarial Networks

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.

Authors

• Jiabin Liu Southeast University
• Bo Wang
• Zhiquan Qi
• YingJie Tian School of Economics and Management, University of Chinese Academy of Sciences Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation at UCAS
• Yong Shi

Keywords

No keywords are indexed for this paper.