Exploring data augmentation: Multi-task methods for molecular property prediction

Computers & Chemical Engineering, vol. 201, pp. 109253

Abstract

The effectiveness of machine learning (ML) for molecular property prediction is often limited by scarce and incomplete experimental datasets. A particular promising approach to facilitate training ML models in low-data regimes is multi-task learning. We investigate how additional molecular data – even potentially sparse or weakly related – can be augmented through multi-task learning to enhance prediction quality. Through controlled experiments on progressively larger subsets of the QM9 dataset [Ruddigkeit et al. (2012), J. Chem. Inf. Model; Ramakrishnan et al. (2014), Sci. Data], we evaluate the conditions under which multi-task learning outperforms single-task models. We extend these insights to a practical real-world dataset of fuel ignition properties that is small and inherently sparse, offering recommendations for augmenting auxiliary data to improve predictive accuracy. This work provides a systematic framework for data augmentation in molecular property prediction, with implications for data-constrained applications.

Authors 4

1. Timo Gervens Aachen Lehrstuhl Informatik 7

   RWTH Aachen University

   Affiliation as printed

   Lehrstuhl Informatik 7, RWTH Aachen University, Aachen, 52074, Germany

2. Alexander Mitsos Aachen Process Systems Engineering (AVT.SVT)

   Forschungszentrum Jülich · Jülich Aachen Research Alliance · RWTH Aachen University

   Affiliation as printed

   Forschungszentrum Jülich GmbH, Institute of Climate and Energy Systems ICE-1 – Energy Systems Engineering, 52425, Jülich, Germany

   JARA Center for Simulation and Data Science (CSD), 52056, Aachen, Germany

   Process Systems Engineering (AVT.SVT), RWTH Aachen University, Aachen, 52074, Germany

3. Martin Grohe Aachen Lehrstuhl Informatik 7

   Jülich Aachen Research Alliance · RWTH Aachen University

   Affiliation as printed

   JARA Center for Simulation and Data Science (CSD), 52056, Aachen, Germany

   Lehrstuhl Informatik 7, RWTH Aachen University, Aachen, 52074, Germany

4. Jan G. Rittig corresponding Aachen Process Systems Engineering (AVT.SVT)

   RWTH Aachen University

   Affiliation as printed

   Process Systems Engineering (AVT.SVT), RWTH Aachen University, Aachen, 52074, Germany