# Integrating Predictive and Generative Capabilities by Latent Space Design via the DKL-VAE Model

arXiv: https://arxiv.org/abs/2503.02978 · HTML: https://mlsanity.com/paper/2503.02978/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 20 of 20)

- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [Constrained Graph Variational Autoencoders for Molecule Design](https://mlsanity.com/paper/1805.09076/) (2018)
- [Neural Architecture Optimization](https://mlsanity.com/paper/1808.07233/) (2018)
- [Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining](https://mlsanity.com/paper/2006.09191/) (2020)
- [Syntax-Directed Variational Autoencoder for Structured Data](https://mlsanity.com/paper/1802.08786/) (2018)
- [Molecular generative model based on conditional variational autoencoder for de novo molecular design](https://mlsanity.com/paper/1806.05805/) (2018)
- [Reconstructing continuous distributions of 3D protein structure from cryo-EM images](https://mlsanity.com/paper/1909.05215/) (2019)
- [High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning](https://mlsanity.com/paper/2106.03609/) (2021)
- [Conditional molecular design with deep generative models](https://mlsanity.com/paper/1805.00108/) (2018)
- [Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy](https://mlsanity.com/paper/1909.06296/) (2019)
- [Explicitly disentangling image content from translation and rotation with spatial-VAE](https://mlsanity.com/paper/1909.11663/) (2019)
- [Bayesian Optimization in Variational Latent Spaces with Dynamic Compression](https://mlsanity.com/paper/1907.04796/) (2019)
- [Deep Kernel Methods Learn Better: From Cards to Process Optimization](https://mlsanity.com/paper/2303.14554/) (2023)
- [Robust Feature Disentanglement in Imaging Data via Joint Invariant Variational Autoencoders: from Cards to Atoms](https://mlsanity.com/paper/2104.10180/) (2021)
- [Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoders](https://mlsanity.com/paper/2106.12472/) (2021)
- [Semi-supervised learning of images with strong rotational disorder: assembling nanoparticle libraries](https://mlsanity.com/paper/2105.11475/) (2021)

## Built on by (most cited first, 3 of 3)

- [Closed-loop discovery of out-of-distribution processing protocols by evolutionary search and uncertainty-aware learning](https://mlsanity.com/paper/2606.13859/) (2026)
- [DIVIDE: A Framework for Learning from Independent Multi-Mechanism Data Using Deep Encoders and Gaussian Processes](https://mlsanity.com/paper/2511.12745/) (2025)
- [Novelty-Driven Target-Space Discovery in Automated Electron and Scanning Probe Microscopy](https://mlsanity.com/paper/2603.16715/) (2026)

## Abstract (arXiv)

We introduce a Deep Kernel Learning Variational Autoencoder (VAE-DKL) framework that integrates the generative power of a Variational Autoencoder (VAE) with the predictive nature of Deep Kernel Learning (DKL). The VAE learns a latent representation of high-dimensional data, enabling the generation of novel structures, while DKL refines this latent space by structuring it in alignment with target properties through Gaussian Process (GP) regression. This approach preserves the generative capabilities of the VAE while enhancing its latent space for GP-based property prediction. We evaluate the framework on two datasets: a structured card dataset with predefined variational factors and the QM9 molecular dataset, where enthalpy serves as the target function for optimization. The model demonstrates high-precision property prediction and enables the generation of novel out-of-training subset structures with desired characteristics. The VAE-DKL framework offers a promising approach for high-throughput material discovery and molecular design, balancing structured latent space organization with generative flexibility.