Learning from Label Proportions with Generative Adversarial Networks
This work addresses the LLP problem for scenarios with limited label information, offering a scalable deep learning solution, though it appears incremental as it builds on existing GAN frameworks.
The paper tackles the problem of learning from label proportions (LLP) by proposing LLP-GAN, a method using generative adversarial networks to derive an instance-level classifier from bag-level label proportions, achieving advantages over existing methods on benchmark datasets.
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.