DeepAI AI Chat
Log In Sign Up

Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching

by   Ziliang Chen, et al.

A broad range of cross-m-domain generation researches boil down to matching a joint distribution by deep generative models (DGMs). Hitherto algorithms excel in pairwise domains while as m increases, remain struggling to scale themselves to fit a joint distribution. In this paper, we propose a domain-scalable DGM, i.e., MMI-ALI for m-domain joint distribution matching. As an m-domain ensemble model of ALIs dumoulin2016adversarially, MMI-ALI is adversarially trained with maximizing Multivariate Mutual Information (MMI) w.r.t. joint variables of each pair of domains and their shared feature. The negative MMIs are upper bounded by a series of feasible losses that provably lead to matching m-domain joint distributions. MMI-ALI linearly scales as m increases and thus, strikes a right balance between efficacy and scalability. We evaluate MMI-ALI in diverse challenging m-domain scenarios and verify its superiority.


page 6

page 7

page 8


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

A new generative adversarial network is developed for joint distribution...

Joint Wasserstein Distribution Matching

Joint distribution matching (JDM) problem, which aims to learn bidirecti...

Learning to Match Distributions for Domain Adaptation

When the training and test data are from different distributions, domain...

Joint Information Preservation for Heterogeneous Domain Adaptation

Domain adaptation aims to assist the modeling tasks of the target domain...

Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization

Contrastive learning (CL) has been successful as a powerful representati...

MaNi: Maximizing Mutual Information for Nuclei Cross-Domain Unsupervised Segmentation

In this work, we propose a mutual information (MI) based unsupervised do...

dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance

AUTOMAP is a promising generalized reconstruction approach, however, it ...