PolyMon: A Unified Framework for Polymer Property Prediction

TL;DR

PolyMon is a comprehensive framework that integrates various polymer representations, machine learning models, and training strategies to improve property prediction accuracy and facilitate systematic benchmarking in polymer materials science.

Contribution

It introduces a unified platform for polymer property prediction that supports multiple representations, models, and training strategies, enabling systematic evaluation and advancement.

Findings

Systematic evaluation of representations and models on five polymer properties.

Demonstration of training strategies to leverage limited data.

PolyMon's extensible platform facilitates benchmarking and method development.

Abstract

Accurate prediction of polymer properties is essential for materials design, but remains challenging due to data scarcity, diverse polymer representations, and the lack of systematic evaluation across modelling choices. Here, we present PolyMon, a unified and accessible framework that integrates multiple polymer representations, machine learning methods, and training strategies within a single, accessible platform. PolyMon supports various descriptors and graph construction strategies for polymer representations, and includes a wide range of models, from tabular models to graph neural networks, along with flexible training strategies including multi-fidelity learning, {\Delta}-learning, active learning, and ensemble learning. Using five key polymer properties as benchmarks, we perform systematic evaluations to assess how representations and models affect predictive performance. These case studies further illustrate how different training strategies can be applied within a consistent workflow to leverage limited data and incorporate physical model derived information. Overall, PolyMon provides a comprehensive and extensible foundation for benchmarking and advancing machine learning-based polymer property prediction. The code is available at github.com/fate1997/polymon.