Augmenting Polymer Datasets by Iterative Rearrangement

30 November 2022, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


One of the biggest obstacles to successful polymer property prediction is an effective representation that accurately captures the sequence of repeat units in a polymer. Motivated by the successes of data augmentation in computer vision and natural language processing, we explore augmenting polymer data by rearranging the molecular representation while preserving the correct connectivity, revealing additional substructural information that is not present in a single representation. We evaluate the effects of this technique on the performance of machine learning models trained on three experimental polymer datasets and compare them to common molecular representations. Data augmentation improves deep learning property prediction performance compared to equivalent (non-augmented) representations. In datasets where the target property is primarily influenced by the polymer sequence rather than experimental parameters, this data augmentation technique provides the molecular embedding with more information to improve property prediction accuracy.


Data Augmentation
Machine Learning
Molecular Representation

Supplementary materials

Supplementary Information: Augmenting Polymer Datasets by Iterative Rearrangement
The supplementary information contains the molecular structures of the polymers and solvents from each dataset, and the data analysis of the original dataset and the augmented dataset.


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.