# Latent Space Bayesian Optimization with Latent Data Augmentation for Enhanced Exploration

arXiv: https://arxiv.org/abs/2302.02399 · HTML: https://mlsanity.com/paper/2302.02399/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 5 Feb 2023.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [Neural Architecture Search with Bayesian Optimisation and Optimal Transport](https://mlsanity.com/paper/1802.07191/) (2018)
- [Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining](https://mlsanity.com/paper/2006.09191/) (2020)
- [Local Latent Space Bayesian Optimization over Structured Inputs](https://mlsanity.com/paper/2201.11872/) (2022)
- [Molecular Hypergraph Grammar with its Application to Molecular Optimization](https://mlsanity.com/paper/1809.02745/) (2018)
- [High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning](https://mlsanity.com/paper/2106.03609/) (2021)
- [Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders](https://mlsanity.com/paper/1804.10469/) (2018)
- [Denoising Criterion for Variational Auto-Encoding Framework](https://mlsanity.com/paper/1511.06406/) (2015)
- [Good practices for Bayesian Optimization of high dimensional structured spaces](https://mlsanity.com/paper/2012.15471/) (2020)
- [Adaptive machine learning for protein engineering](https://mlsanity.com/paper/2106.05466/) (2021)
- [Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation](https://mlsanity.com/paper/1910.00698/) (2019)

## Built on by (most cited first, 5 of 5)

- [Bayesian Optimization for Controlled Image Editing via LLMs](https://mlsanity.com/paper/2502.18116/) (2025)
- [Crystal-LSBO: Automated Design of De Novo Crystals with Latent Space Bayesian Optimization](https://mlsanity.com/paper/2405.17881/) (2024)
- [Conditional Latent Space Molecular Scaffold Optimization for Accelerated Molecular Design](https://mlsanity.com/paper/2411.01423/) (2024)
- [Bayesian Optimization for Simultaneous Selection of Machine Learning Algorithms and Hyperparameters on Shared Latent Space](https://mlsanity.com/paper/2502.09329/) (2025)
- [Sample-Efficient Optimisation over the Outputs of Generative Models](https://mlsanity.com/paper/2509.23800/) (2025)

## Abstract (arXiv)

Latent Space Bayesian Optimization (LSBO) combines generative models, typically Variational Autoencoders (VAE), with Bayesian Optimization (BO) to generate de-novo objects of interest. However, LSBO faces challenges due to the mismatch between the objectives of BO and VAE, resulting in poor exploration capabilities. In this paper, we propose novel contributions to enhance LSBO efficiency and overcome this challenge. We first introduce the concept of latent consistency/inconsistency as a crucial problem in LSBO, arising from the VAE-BO mismatch. To address this, we propose the Latent Consistent Aware-Acquisition Function (LCA-AF) that leverages consistent points in LSBO. Additionally, we present LCA-VAE, a novel VAE method that creates a latent space with increased consistent points through data augmentation in latent space and penalization of latent inconsistencies. Combining LCA-VAE and LCA-AF, we develop LCA-LSBO. Our approach achieves high sample-efficiency and effective exploration, emphasizing the significance of addressing latent consistency through the novel incorporation of data augmentation in latent space within LCA-VAE in LSBO. We showcase the performance of our proposal via de-novo image generation and de-novo chemical design tasks.