Print Email Facebook Twitter Mixed-integer optimisation of graph neural networks for computer-aided molecular design 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 networksGraphSAGEMixed integer programmingMolecular designOptimal 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 Files file embargo until 2024-09-22