DeepAI AI Chat
Log In Sign Up

Improving black-box optimization in VAE latent space using decoder uncertainty

by   Pascal Notin, et al.

Optimization in the latent space of variational autoencoders is a promising approach to generate high-dimensional discrete objects that maximize an expensive black-box property (e.g., drug-likeness in molecular generation, function approximation with arithmetic expressions). However, existing methods lack robustness as they may decide to explore areas of the latent space for which no data was available during training and where the decoder can be unreliable, leading to the generation of unrealistic or invalid objects. We propose to leverage the epistemic uncertainty of the decoder to guide the optimization process. This is not trivial though, as a naive estimation of uncertainty in the high-dimensional and structured settings we consider would result in high estimator variance. To solve this problem, we introduce an importance sampling-based estimator that provides more robust estimates of epistemic uncertainty. Our uncertainty-guided optimization approach does not require modifications of the model architecture nor the training process. It produces samples with a better trade-off between black-box objective and validity of the generated samples, sometimes improving both simultaneously. We illustrate these advantages across several experimental settings in digit generation, arithmetic expression approximation and molecule generation for drug design.


page 2

page 7

page 17


Improving Small Molecule Generation using Mutual Information Machine

We address the task of controlled generation of small molecules, which e...

Probabilistic Autoencoder using Fisher Information

Neural Networks play a growing role in many science disciplines, includi...

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining

Many important problems in science and engineering, such as drug design,...

High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning

We introduce a method based on deep metric learning to perform Bayesian ...

Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies

Discrete variational auto-encoders (VAEs) are able to represent semantic...

Text Counterfactuals via Latent Optimization and Shapley-Guided Search

We study the problem of generating counterfactual text for a classifier ...