基于机器学习的聚合物性能预测开放基准

arXiv cs.LG 论文
machine-learning polymers benchmark open-source research

摘要

论文介绍了Polymer Benchmark 2026，这是一个开放数据集，旨在对聚合物性能预测中的机器学习方法进行基准测试，涵盖多种架构和性能。

arXiv:2609.27036v1 Announce Type: new Abstract: Polymer property prediction lacks open, standardized benchmarks that enable rigorous comparison of machine-learning methods, with existing resources covering only a narrow fraction of polymer architectures, such as homopolymers. We introduce Polymer Benchmark 2026 (PolyBench26), an open dataset comprising nearly 250,000 polymer-property datapoints across eight physical properties, including data from experimental measurements, density functional theory, and molecular dynamics. The benchmark supports four evaluation tasks across homopolymers and alternating, random, and block copolymers: in-distribution property prediction, dataset-size scaling, repeat-unit complexity, and transfer to held-out polymer architectures. We compare language model, graph-based, and descriptor-based approaches and find graph-based models provide the lowest errors in property prediction, retain their advantage across the evaluated training-set sizes, and remain robust to increasing repeat-unit complexity. PolyBench26 provides a reproducible foundation for developing models for the increasingly complex polymer design space. The PolyBench26 benchmark is available open-source at https://github.com/rlearsch/PolymerBenchmark2026.
查看原文
查看缓存全文

缓存时间: 2026/09/24 09:35 

# An open benchmark for machine learning-based polymer property prediction
Source: [https://arxiv.org/abs/2609.27036](https://arxiv.org/abs/2609.27036)
[View PDF](https://arxiv.org/pdf/2609.27036)

> Abstract:Polymer property prediction lacks open, standardized benchmarks that enable rigorous comparison of machine\-learning methods, with existing resources covering only a narrow fraction of polymer architectures, such as homopolymers\. We introduce Polymer Benchmark 2026 \(PolyBench26\), an open dataset comprising nearly 250,000 polymer\-property datapoints across eight physical properties, including data from experimental measurements, density functional theory, and molecular dynamics\. The benchmark supports four evaluation tasks across homopolymers and alternating, random, and block copolymers: in\-distribution property prediction, dataset\-size scaling, repeat\-unit complexity, and transfer to held\-out polymer architectures\. We compare language model, graph\-based, and descriptor\-based approaches and find graph\-based models provide the lowest errors in property prediction, retain their advantage across the evaluated training\-set sizes, and remain robust to increasing repeat\-unit complexity\. PolyBench26 provides a reproducible foundation for developing models for the increasingly complex polymer design space\. The PolyBench26 benchmark is available open\-source at[this https URL](https://github.com/rlearsch/PolymerBenchmark2026)\.

## Submission history

From: Robert Learsch \[[view email](https://arxiv.org/show-email/4458999e/2609.27036)\] **\[v1\]**Tue, 22 Sep 2026 20:32:53 UTC \(1,463 KB\)

相似文章

用于分子属性预测的程序化预训练

arXiv cs.LG

本文介绍了一种三阶段训练流水线，通过程序化预训练提升分子属性预测性能，在数据稀缺情况下通过从抽象生成数据中学习归纳偏置，表现出更优性能。