PolyCL: contrastive learning for polymer representation learning via explicit and implicit augmentations
Digital Discovery · 2025 · 4 (1) · 149-160
DOI: 10.1039/d4dd00236a ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Discovery, 2025. Verfasst von Jiajun Zhou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, Molecular Sciences Research Hub, Imperial College London White City Campus, Wood Lane London W12 0BZ UK k.jelfs@imperial.ac.…. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0). Gefördert von: H2020 European Research Council, Royal Society, Engineering and Physical Sciences Research Council.
Abstract (Originalsprache)
We introduce PolyCL, a self-supervised contrastive learning model for robust polymer representation. Combining explicit and implicit augmentations, PolyCL excels in downstream predictive tasks without complex finetuning.
Autor:innen und Institutionen
- Department of Chemistry, Molecular Sciences Research Hub, Imperial College London White City Campus, Wood Lane London W12 0BZ UK k.jelfs@imperial.ac.uk.
- I-X Centre for AI in Science, Imperial College London White City Campus, Wood Lane London W12 0BZ UK.
ORCID-Profile: Jiajun Zhou, Yijie Yang, Austin M Mroz, Kim E Jelfs
Förderung
- H2020 European Research Council
- Royal Society
- Engineering and Physical Sciences Research Council
- Schmidt Family Foundation
Zitieren
APA
Zhou, J., Yang, Y., Mroz, A. M., & Jelfs, K. E. (2025). PolyCL: contrastive learning for polymer representation learning via explicit and implicit augmentations. Digital Discovery, 4(1), 149-160. https://doi.org/10.1039/d4dd00236a
Vancouver
Zhou J, Yang Y, Mroz AM, Jelfs KE. PolyCL: contrastive learning for polymer representation learning via explicit and implicit augmentations. Digital Discovery. 2025;4(1):149-160. doi:10.1039/d4dd00236a
BibTeX
@article{Zhou2025,
author = {Zhou, Jiajun and Yang, Yijie and Mroz, Austin M and Jelfs, Kim E},
title = {PolyCL: contrastive learning for polymer representation learning via explicit and implicit augmentations},
journal = {Digital Discovery},
year = {2025},
volume = {4},
number = {1},
pages = {149--160},
doi = {10.1039/d4dd00236a}
}
EUVIMED