# Generative-Discriminative Complementary Learning

arXiv: https://arxiv.org/abs/1904.01612 · HTML: https://mlsanity.com/paper/1904.01612/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [Reduction from Complementary-Label Learning to Probability Estimates](https://mlsanity.com/paper/2209.09500/) (2022)
- [Class-Imbalanced Complementary-Label Learning via Weighted Loss](https://mlsanity.com/paper/2209.14189/) (2022)
- [CLImage: Human-Annotated Datasets for Complementary-Label Learning](https://mlsanity.com/paper/2305.08295/) (2023)
- [Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation](https://mlsanity.com/paper/2312.16478/) (2023)
- [ProPaLL: Probabilistic Partial Label Learning](https://mlsanity.com/paper/2208.09931/) (2022)
- [Complementary to Multiple Labels: A Correlation-Aware Correction Approach](https://mlsanity.com/paper/2302.12987/) (2023)
- [SCLNet: A Scale-Robust Complementary Learning Network for Object Detection in UAV Images](https://mlsanity.com/paper/2409.07024/) (2024)
- [Complementary Labels Learning with Augmented Classes](https://mlsanity.com/paper/2211.10701/) (2022)
- [Learning from Stochastic Labels](https://mlsanity.com/paper/2302.00299/) (2023)
- [Learning from Complementary Features](https://mlsanity.com/paper/2408.14788/) (2024)
- [ScarceGAN: Discriminative Classification Framework for Rare Class Identification for Longitudinal Data with Weak Prior](https://mlsanity.com/paper/2505.03811/) (2025)
- [Learning from Uncertain Similarity and Unlabeled Data](https://mlsanity.com/paper/2509.11984/) (2025)

## Abstract (arXiv)

Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and can generate high-quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarily-labeled data.