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 \cite{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.
@article{arxiv.1907.03426,
title = {Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching},
author = {Ziliang Chen and Zhanfu Yang and Xiaoxi Wang and Xiaodan Liang and Xiaopeng Yan and Guanbin Li and Liang Lin},
journal= {arXiv preprint arXiv:1907.03426},
year = {2019}
}