A Systematic Comparison Study on Hyperparameter Optimisation of Graph Neural Networks for Molecular Property Prediction

Yingfang Yuan, Wenjun Wang, Wei Pang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)
54 Downloads (Pure)

Abstract

Graph neural networks (GNNs) have been proposed for a wide range of graph-related learning tasks. In particular, in recent years, an increasing number of GNN systems were applied to predict molecular properties. However, a direct impediment is to select appropriate hyperparameters to achieve satisfactory performance with lower computational cost. Meanwhile, many molecular datasets are far smaller than many other datasets in typical deep learning applications. Most hyperparameter optimization (HPO) methods have not been explored in terms of their efficiencies on such small datasets in the molecular domain. In this paper, we conducted a theoretical analysis of common and specific features for two state-of-the-art and popular algorithms for HPO: TPE and CMA-ES, and we compared them with random search (RS), which is used as a baseline. Experimental studies are carried out on several benchmarks in MoleculeNet, from different perspectives to investigate the impact of RS, TPE, and CMA-ES on HPO of GNNs for molecular property prediction. In our experiments, we concluded that RS, TPE, and CMA-ES have their individual advantages in tackling different specific molecular problems. Finally, we believe our work will motivate further research on GNN as applied to molecular machine learning problems in chemistry and materials sciences.
Original languageEnglish
Title of host publicationGECCO '21: Proceedings of the Genetic and Evolutionary Computation Conference
PublisherAssociation for Computing Machinery
Pages386–394
Number of pages9
ISBN (Print)9781450383509
DOIs
Publication statusPublished - 26 Jun 2021
EventGenetic and Evolutionary Computation Conference 2021 - Lille, France
Duration: 10 Jul 202114 Jul 2021
https://gecco-2021.sigevo.org/HomePage

Conference

ConferenceGenetic and Evolutionary Computation Conference 2021
Abbreviated titleGECCO 2021
Country/TerritoryFrance
CityLille
Period10/07/2114/07/21
Internet address

Keywords

  • Graph neural networks
  • Hyperparameter optimisation
  • Molecular property prediction

ASJC Scopus subject areas

  • Genetics
  • Computational Mathematics

Fingerprint

Dive into the research topics of 'A Systematic Comparison Study on Hyperparameter Optimisation of Graph Neural Networks for Molecular Property Prediction'. Together they form a unique fingerprint.

Cite this