JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets

By Yunchen Pu, Shuyang Dai, Zhe Gan, Weiyao Wang, Guoyin Wang, Yizhe Zhang, Ricardo Henao, Lawrence Carin. 2018

44 citations recorded by the source corpus.

A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional distributions between the domains, while simultaneously learning to sample from the marginals of each individual domain. The proposed framework consists of multiple generators and a single softmax-based critic, all jointly trained via adversarial learning. From a simple noise source, the proposed framework allows synthesis of draws from the marginals, conditional draws given observations from a subset of random variables, or complete draws from the full joint distribution. Most examples considered are for joint analysis of two domains, with examples for three domains also presented.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jianfeng Gao
2. Chunyuan Li
3. Zhe Gan
4. Michel Galley
5. Chris Brockett
6. William B. Dolan
7. Yizhe Zhang
8. Mohit Bansal

In Computer Vision and Pattern Recognition

1. Chunyuan Li
2. Jianfeng Gao
3. Zhe Gan
4. Jun Zhu
5. Luc Van Gool
6. Dacheng Tao
7. Cordelia Schmid
8. Chongxuan Li

In Generative Models

1. Chunyuan Li
2. Jun Zhu
3. Jianfeng Gao
4. Chongxuan Li
5. Yizhe Zhang
6. Zhe Gan
7. Kun Xu
8. Michel Galley

In Representation & Self-Supervised Learning

1. Chunyuan Li
2. Yizhe Zhang
3. Jianfeng Gao
4. Michel Galley
5. Zhe Gan
6. Jun Zhu
7. Kun Xu
8. Bo Zhang

Citations in the corpus

• Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization (2018, methodology): “We also employ a dual adversarial objective inspired by [13, 14, 15], which composes both source-to-target (forward) and target-to-source (backward) objectives.”
• Towards Better Representations with Deep/Bayesian Learning (2018, background): “…et al., 2016a; Pu et al., 2016a,b; Chen et al., 2018b; Li et al., 2018a; Pu et al., 2017b; Chen et al., 2018a; Xu et al., 2017; Wang et al., 2017b; Pu et al., 2018b; Yuan et al., 2017, 2018; Chapfuwa et al., 2018), sigmoid belief networks (Gan et al., 2015b,c,a; Zhang et al., 2016a; Henao et al.,…”
• Triple Generative Adversarial Networks (2019, background): “JointGAN [59] extends ALI to multiple domains and achieves excellent results.”