Learning from Label Proportions with Generative Adversarial Networks

09/05/2019
by   Jiabin Liu, et al.
0

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.

READ FULL TEXT

page 2

page 8

research
02/19/2019

Label-Removed Generative Adversarial Networks Incorporating with K-Means

Generative Adversarial Networks (GANs) have achieved great success in ge...
research
05/14/2018

Generative Adversarial Forests for Better Conditioned Adversarial Learning

In recent times, many of the breakthroughs in various vision-related tas...
research
06/01/2018

Unsupervised Object Localization using Generative Adversarial Networks

This paper introduces a novel end-to-end deep neural network model for u...
research
02/26/2017

Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

Despite the successes in capturing continuous distributions, the applica...
research
08/02/2018

Physics-Based Generative Adversarial Models for Image Restoration and Beyond

We present an algorithm to directly solve numerous image restoration pro...
research
11/12/2018

Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification

Recent work has shown that exploiting relations between labels improves ...
research
02/28/2020

Distributionally Robust Chance Constrained Programming with Generative Adversarial Networks (GANs)

This paper presents a novel deep learning based data-driven optimization...

Please sign up or login with your details

Forgot password? Click here to reset