Work

Improving generative inverse design of molecular catalysts in small data regime

Year: 2025

Type: article

Abstract: Deep generative models are a powerful tool for exploring the chemical space within inverse-design workflows; however, their effectiveness relies on sufficient training data and effective mechanisms for guiding the model to optimize specific properties. We demonstrate that designing an expert-informed data representation and training procedure allows leveraging data augmentation while maintaining the required sampling controllability. We focus our discussion on a specific class of compounds (transition metal complexes), and a popular class of generative models (equivariant diffusion models), although we envision that the approach could be extended to other chemical spaces and model types. Through experiments, we demonstrate that augmenting the training database with generic but related unlabeled data enables a practical level of performance to be reached.

Source: Machine Learning Science and Technology

DOI: 10.1088/2632-2153/addc32

Authors: François Cornet, Pratham Deshmukh, Bardi Benediktsson, Mikkel N Schmidt, Arghya Bhowmik

Institution: Technical University of Denmark

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,000

Funder: Danmarks Frie Forskningsfond