


















Authors:H. Ibrahim Erdogan (University of Bayreuth, Germany), Punith Raviswamy (University of Bayreuth, Germany), Nikita Agrawal (University of Bayreuth, Germany), Yannik Köster (Friedrich Schiller University Jena, Germany), Stefan Zechel (Friedrich Schiller University Jena, Germany), Ulrich S. Schubert (Friedrich Schiller University Jena, Germany), Ruben Mayer (University of Bayreuth, Germany), Christopher Kuenneth (University of Bayreuth, Germany)
Abstract:Graph Neural Networks (GNNs) have achieved strong results in molecular property prediction, but polymers present distinct challenges: labeled datasets are scarce and small (typically in the order of hundreds of polymers) due to the need for expensive experimentation, and complex polymer chain distributions influence polymer properties. Established practice in polymer prediction represents polymers solely by graphs of their repeat units, discarding the chain-scale morphology that governs key properties such as the glass transition temperature ($T_g$). In this work, we propose a principled graph construction that addresses this gap. Given a polymer's molecular mass distribution (MMD), we sample representative chains from the Schulz-Zimm distribution and construct representative sets of large graphs encoding chain-scale topology directly, with atoms and bonds featurized using rich chemical descriptors. We further pretrain GNN encoders via masked graph modeling on 100,000 unlabeled PSMILES strings before fine-tuning on labeled data. On a dataset of 381 polymers (180 homopolymers and 201 copolymers), we show that graph construction and self-supervised pretraining are jointly necessary: without pretraining, the large graph method matches the repeat-unit baseline (28.40 K vs. 28.36 K RMSE); with pretraining, it achieves 24.76 K +/- 3.30 K, a 5.1% reduction in mean error over the pretrained repeat-unit baseline (26.08 K +/- 4.20 K, p < 0.001, 30 runs). An ablation removing chemical features degrades performance to 36.65 K, confirming both components are essential. Results are architecture-agnostic, holding for both GINE and GATv2 encoders.
| Comments: | 9 pages, 4 figures |
| Subjects: | Machine Learning (cs.LG) |
| ACM classes: | I.2.6; J.2 |
| Cite as: | arXiv:2605.10551 [cs.LG] |
| (or arXiv:2605.10551v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10551 arXiv-issued DOI via DataCite (pending registration) |
From: Halil Ibrahim Erdogan [view email]
[v1]
Mon, 11 May 2026 13:28:40 UTC (224 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。