# Triangle Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1709.06548 · HTML: https://mlsanity.com/paper/1709.06548/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2017.

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

- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [Free Lunch for Domain Adversarial Training: Environment Label Smoothing](https://mlsanity.com/paper/2302.00194/) (2023)
- [Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbations](https://mlsanity.com/paper/2110.11998/) (2021)
- [Collaborative Learning to Generate Audio-Video Jointly](https://mlsanity.com/paper/2104.02656/) (2021)
- [PluGeN: Multi-Label Conditional Generation From Pre-Trained Models](https://mlsanity.com/paper/2109.09011/) (2021)
- [Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data](https://mlsanity.com/paper/2301.11174/) (2023)
- [A Unified View of cGANs with and without Classifiers](https://mlsanity.com/paper/2111.01035/) (2021)
- [Fostering Diversity in Spatial Evolutionary Generative Adversarial Networks](https://mlsanity.com/paper/2106.13590/) (2021)
- [Semi-Supervised Image-to-Image Translation using Latent Space Mapping](https://mlsanity.com/paper/2203.15241/) (2022)
- [Joint-stochastic-approximation Random Fields with Application to Semi-supervised Learning](https://mlsanity.com/paper/2505.20330/) (2025)
- [Semi-Supervised Learning under General Causal Models](https://mlsanity.com/paper/2510.22567/) (2025)

## Abstract (arXiv)

A Triangle Generative Adversarial Network (Delta-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples. Delta-GAN consists of four neural networks, two generators and two discriminators. The generators are designed to learn the two-way conditional distributions between the two domains, while the discriminators implicitly define a ternary discriminative function, which is trained to distinguish real data pairs and two kinds of fake data pairs. The generators and discriminators are trained together using adversarial learning. Under mild assumptions, in theory the joint distributions characterized by the two generators concentrate to the data distribution. In experiments, three different kinds of domain pairs are considered, image-label, image-image and image-attribute pairs. Experiments on semi-supervised image classification, image-to-image translation and attribute-based image generation demonstrate the superiority of the proposed approach.