Saved in:
Bibliographic Details
Main Authors: Jung, Wonjin, Choi, Yongseok
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10893
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911276757680128
author Jung, Wonjin
Choi, Yongseok
author_facet Jung, Wonjin
Choi, Yongseok
contents We address polymer property prediction with a multi-view design that exploits complementary representations. Our system integrates four families: (i) tabular RDKit/Morgan descriptors, (ii) graph neural networks, (iii) 3D-informed representations, and (iv) pretrained SMILES language models, and averages per-property predictions via a uniform ensemble. Models are trained with 10-fold splits and evaluated with SMILES test-time augmentation. The approach ranks 9th of 2241 teams in the Open Polymer Prediction Challenge at NeurIPS 2025. The submitted ensemble achieves a public MAE of 0.057 and a private MAE of 0.082.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10893
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-View Polymer Representations for the Open Polymer Prediction
Jung, Wonjin
Choi, Yongseok
Machine Learning
We address polymer property prediction with a multi-view design that exploits complementary representations. Our system integrates four families: (i) tabular RDKit/Morgan descriptors, (ii) graph neural networks, (iii) 3D-informed representations, and (iv) pretrained SMILES language models, and averages per-property predictions via a uniform ensemble. Models are trained with 10-fold splits and evaluated with SMILES test-time augmentation. The approach ranks 9th of 2241 teams in the Open Polymer Prediction Challenge at NeurIPS 2025. The submitted ensemble achieves a public MAE of 0.057 and a private MAE of 0.082.
title Multi-View Polymer Representations for the Open Polymer Prediction
topic Machine Learning
url https://arxiv.org/abs/2511.10893