Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design

TL;DR

This paper introduces a method to quantify epistemic uncertainty in deep generative models for molecular design by leveraging active subspaces, enabling uncertainty estimation without altering existing models.

Contribution

It proposes a novel active subspace-based uncertainty quantification scheme for deep generative models, applicable to pre-trained models without architectural changes.

Findings

Effective uncertainty estimation demonstrated in molecular design tasks

Enhanced exploration of model diversity under epistemic uncertainty

Applicable to various pre-trained generative models

Abstract

Deep generative models have been accelerating the inverse design process in material and drug design. Unlike their counterpart property predictors in typical molecular design frameworks, generative molecular design models have seen fewer efforts on uncertainty quantification (UQ) due to computational challenges in Bayesian inference posed by their large number of parameters. In this work, we focus on the junction-tree variational autoencoder (JT-VAE), a popular model for generative molecular design, and address this issue by leveraging the low dimensional active subspace to capture the uncertainty in the model parameters. Specifically, we approximate the posterior distribution over the active subspace parameters to estimate the epistemic model uncertainty in an extremely high dimensional parameter space. The proposed UQ scheme does not require alteration of the model architecture, making it readily applicable to any pre-trained model. Our experiments demonstrate the efficacy of the AS-based UQ and its potential impact on molecular optimization by exploring the model diversity under epistemic uncertainty.