Multi-objective Deep Data Generation with Correlated Property Control

Shiyu Wang, Xiaojie Guo, Xuanyang Lin, Bo Pan, Yuanqi Du, Yinkai Wang, Yanfang Ye, Ashley Ann Petersen, Austin Leitgeb, Saleh AlKhalifa, Kevin Minbiole, William Wuest, Amarda Shehu, Liang Zhao

Keywords: deep generative models, controllable generation, correlated properties, disentangled learning, variational autoencoders

TL;DR: We proposed a novel deep generative framework that controls correlated properties of interest while handling correlation and conflicts of properties under a multi-objective optimization scheme.

Abstract: Developing deep generative models has been an emerging field due to the ability to model and generate complex data for various purposes, such as image synthesis and molecular design. However, the advance of deep generative models is limited by the challenges to generate objects that possess multiple desired properties because: 1) the existence of complex correlation among real-world properties is common but hard to identify; 2) controlling individual property enforces an implicit partially control of its correlated properties, which is difficult to model; 3) controlling multiple properties under variour manners simultaneously is hard and underexplored. We address these challenges by proposing a novel deep generative framework that recovers semantics and correlation of properties through disentangled latent vectors. The correlation is handled via an explainable mask pooling layer, and properties are precisely retained by the generated objects via the mutual dependence between latent vectors and properties. Our generative model preserves properties of interest while handles correlation and conflicts of properties under a multi-objective optimization framework. The experiments demonstrate our model's superior performance in generating objects with desired properties.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2210.01796/code)