Mixed-integer optimisation of graph neural networks for computer-aided molecular design

Journal Article (2024)
Author(s)

Tom McDonald (Student TU Delft)

Calvin Tsay (Imperial College London)

A.M. Schweidtmanna (TU Delft - ChemE/Process Systems Engineering)

N. Yorke-Smith (TU Delft - Algorithmics)

Research Group
ChemE/Process Systems Engineering
DOI related publication
https://doi.org/10.1016/j.compchemeng.2024.108660
More Info
expand_more
Publication Year
2024
Language
English
Research Group
ChemE/Process Systems Engineering
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. @en
Volume number
185
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

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.

Files

1-s2.0-S0098135424000784-main.... (pdf)
(pdf | 1.93 Mb)
- Embargo expired in 22-09-2024
License info not available