Multi-objective Deep Data Generation with Correlated Property Control

TL;DR

This paper introduces a deep generative framework that effectively models and controls multiple correlated properties in generated data, addressing complex property correlations and enabling precise multi-property data synthesis.

Contribution

The proposed model uniquely recovers property semantics and correlations using disentangled latent vectors and an explainable mask pooling layer, advancing multi-property control in deep data generation.

Findings

Outperforms existing models in generating data with desired properties

Effectively models complex correlations among multiple properties

Demonstrates superior property preservation in generated data

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 advancement of deep generative models is limited by challenges to generate objects that possess multiple desired properties: 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 various manners simultaneously is hard and under-explored. We address these challenges by proposing a novel deep generative framework that recovers semantics and the correlation of properties through disentangled latent vectors. The correlation is handled via an explainable mask pooling layer, and properties are precisely retained by generated objects via the mutual dependence between latent vectors and properties. Our generative model preserves properties of interest while handling correlation and conflicts of properties under a multi-objective optimization framework. The experiments demonstrate our model's superior performance in generating data with desired properties.