Integrating Predictive and Generative Capabilities by Latent Space Design via the DKL-VAE Model
Open Access
- 6 July 2026
- journal article
- research article
- Published by Springer Nature in npj Computational Materials
- Vol. 12 (1) , 231
Abstract
: We introduce a deep Kernel learning variational autoencoder (DKL-VAE) 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 DKL-VAE framework offers a promising approach for high-throughput material discovery and molecular design, balancing structured latent space organization with generative flexibility.Keywords
All Related Versions
Funding Information
- AI Tennessee Initiative at University of Tennessee Knoxville
- Laboratory Directed Research and Development Program at Pacific Northwest National Laboratory
- U.S. Department of Energy (DE-SC0019288)
This publication has 29 references indexed in Scilit:
- Exploring the Relationship of Microstructure and Conductivity in Metal Halide Perovskites via Active Learning-Driven Automated Scanning Probe MicroscopyThe Journal of Physical Chemistry Letters, 2023
- Physics Discovery in Nanoplasmonic Systems via Autonomous Experiments in Scanning Transmission Electron MicroscopyAdvanced Science, 2022
- Automated Experiments of Local Non‐Linear Behavior in Ferroelectric MaterialsSmall, 2022
- A review of molecular representation in the age of machine learningWIREs Computational Molecular Science, 2022
- Exploring Causal Physical Mechanisms via Non-Gaussian Linear Models and Deep Kernel Learning: Applications for Ferroelectric Domain StructuresACS Nano, 2021
- Disentangling Rotational Dynamics and Ordering Transitions in a System of Self-Organizing Protein Nanorods via Rotationally Invariant Latent RepresentationsACS Nano, 2021
- Embedding high-dimensional Bayesian optimization via generative modeling: Parameter personalization of cardiac electrophysiological modelsMedical Image Analysis, 2020
- Conditional Molecular Design with Deep Generative ModelsJournal of Chemical Information and Modeling, 2018
- Automatic Chemical Design Using a Data-Driven Continuous Representation of MoleculesACS Central Science, 2018
- Deep Generative Models for Molecular ScienceMolecular Informatics, 2018