Title
Mixed-integer optimisation of graph neural networks for computer-aided molecular design
Author
McDonald, Tom (Student TU Delft)
Tsay, Calvin (Imperial College London)
Schweidtmann, A.M. (TU Delft ChemE/Process Systems Engineering)
Yorke-Smith, N. (TU Delft Algorithmics)
Date
2024
Abstract
ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP), enabling surrogate-based optimisation in various domains and efficient solution of machine learning certification problems. However, previous works are mostly limited to MLPs. Graph neural networks (GNNs) can learn from non-euclidean data structures such as molecular structures efficiently and are thus highly relevant to computer-aided molecular design (CAMD). We propose a bilinear formulation for ReLU Graph Convolutional Neural Networks and a MILP formulation for ReLU GraphSAGE models. These formulations enable solving optimisation problems with trained GNNs embedded to global optimality. We apply our optimisation approach to an illustrative CAMD case study where the formulations of the trained GNNs are used to design molecules with optimal boiling points.
Subject
Graph neural networks
GraphSAGE
Mixed integer programming
Molecular design
Optimal boiling point
To reference this document use:
http://resolver.tudelft.nl/uuid:d9904329-087a-4799-8327-e0159a30be88
DOI
https://doi.org/10.1016/j.compchemeng.2024.108660
Embargo date
2024-09-22
ISSN
0098-1354
Source
Computers & Chemical Engineering, 185
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
journal article
Rights
© 2024 Tom McDonald, Calvin Tsay, A.M. Schweidtmann, N. Yorke-Smith