# Learning from Label Proportions with Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1909.02180 · HTML: https://mlsanity.com/paper/1909.02180/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [Learning from Label Proportions by Learning with Label Noise](https://mlsanity.com/paper/2203.02496/) (2022)
- [Two-stage Training for Learning from Label Proportions](https://mlsanity.com/paper/2105.10635/) (2021)
- [PAC Learning Linear Thresholds from Label Proportions](https://mlsanity.com/paper/2310.10098/) (2023)
- [Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization](https://mlsanity.com/paper/2302.08947/) (2023)
- [MixBag: Bag-Level Data Augmentation for Learning from Label Proportions](https://mlsanity.com/paper/2308.08822/) (2023)
- [Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization](https://mlsanity.com/paper/2207.01555/) (2022)
- [Learning from Partial Label Proportions for Whole Slide Image Segmentation](https://mlsanity.com/paper/2405.09041/) (2024)
- [Fast learning from label proportions with small bags](https://mlsanity.com/paper/2110.03426/) (2021)
- [Learning crop type mapping from regional label proportions in large-scale SAR and optical imagery](https://mlsanity.com/paper/2208.11607/) (2022)
- [LLP-Bench: A Large Scale Tabular Benchmark for Learning from Label Proportions](https://mlsanity.com/paper/2310.10096/) (2023)
- [Nearly Optimal Sample Complexity for Learning with Label Proportions](https://mlsanity.com/paper/2505.05355/) (2025)
- [Learning from Label Proportions with Instance-wise Consistency](https://mlsanity.com/paper/2203.12836/) (2022)
- [Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bags](https://mlsanity.com/paper/2408.14130/) (2024)
- [Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions](https://mlsanity.com/paper/2411.10364/) (2024)
- [Label Differential Privacy via Aggregation](https://mlsanity.com/paper/2310.10092/) (2023)
- [Learning under Label Proportions for Text Classification](https://mlsanity.com/paper/2310.11707/) (2023)
- [Optimal Learning from Label Proportions with General Loss Functions](https://mlsanity.com/paper/2509.15145/) (2025)
- [Evaluating LLP Methods: Challenges and Approaches](https://mlsanity.com/paper/2310.19065/) (2023)
- [FRACTAL: Fine-Grained Scoring from Aggregate Text Labels](https://mlsanity.com/paper/2404.04817/) (2024)
- [Weak to Strong Learning from Aggregate Labels](https://mlsanity.com/paper/2411.06200/) (2024)
- [Learning from Label Proportions and Covariate-shifted Instances](https://mlsanity.com/paper/2411.12334/) (2024)
- [Aggregating Data for Optimal and Private Learning](https://mlsanity.com/paper/2411.19045/) (2024)
- [Learning from N-Tuple Data with M Positive Instances: Unbiased Risk Estimation and Theoretical Guarantees](https://mlsanity.com/paper/2510.18406/) (2025)
- [Learning from Label Proportions with Dual-proportion Constraints](https://mlsanity.com/paper/2603.21153/) (2026)
- [Multi-Label Proportion Learning for Sea-Ice Type Prediction](https://mlsanity.com/paper/2609.16347/) (2026)

## Abstract (arXiv)

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.