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

Yunchen Pu, Shuyang Dai, Zhe Gan, Weiyao Wang, Guoyin Wang, Yizhe Zhang, Ricardo Henao, Lawrence Carin Duke
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:4151-4160, 2018.

Abstract

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-pu18a, title = {{J}oint{GAN}: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets}, author = {Pu, Yunchen and Dai, Shuyang and Gan, Zhe and Wang, Weiyao and Wang, Guoyin and Zhang, Yizhe and Henao, Ricardo and Duke, Lawrence Carin}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {4151--4160}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/pu18a/pu18a.pdf}, url = {https://proceedings.mlr.press/v80/pu18a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets %A Yunchen Pu %A Shuyang Dai %A Zhe Gan %A Weiyao Wang %A Guoyin Wang %A Yizhe Zhang %A Ricardo Henao %A Lawrence Carin Duke %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-pu18a %I PMLR %P 4151--4160 %U https://proceedings.mlr.press/v80/pu18a.html %V 80 %X 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.
APA
Pu, Y., Dai, S., Gan, Z., Wang, W., Wang, G., Zhang, Y., Henao, R. & Duke, L.C.. (2018). JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:4151-4160 Available from https://proceedings.mlr.press/v80/pu18a.html.

Related Material