Multi-View Polymer Representations for the Open Polymer Prediction
This work addresses polymer property prediction for materials science, but it is incremental as it combines existing methods without introducing new paradigms.
The paper tackled polymer property prediction by integrating four complementary representation families into a uniform ensemble, achieving 9th place out of 2241 teams in the Open Polymer Prediction Challenge with a private MAE of 0.082.
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.